Skills/Glama/live-comments

live-comments@r1

VERIFIED· install only

Publisher claims: "Exposes a read_source tool that lets agents read cited tickets, docs, and files through the same path the checker verifies, so quoted business rules match their sources and stay in sync as those sources or their authors change. It also keeps undecided product decisions explicit as open questions rather than letting agents invent answers." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher bicameralai · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add live-comments
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso atlassian.com, google.com, linear.app, notion.com, notion.so, slack.com, nango.dev — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is live-comments@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Fake instruction boundary tagskills/live-comments/SKILL.md:17 · Fake instruction boundary tag…e. 4. **Authority.** Draft person definitions from `npx live-comments directory <system>` and `git log` authors, then groups and places from the teams the user describe…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagskills/live-comments/SKILL.md:75 · Fake instruction boundary tag… members(linear:team/PRICING)`. Get exact ids from `npx live-comments directory <system>` rather than guessing them. Show the definition to the user and add it to `AUTH…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagskills/live-comments/SKILL.md:16 · Fake instruction boundary tag3. **Sources.** Ask the user which tools their decisions live in, and have them run `npx live-comments connect <system>` for each one.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandpackages/cli/package.json:10 · File permission modification command — agent changes file ownership/permissions"build": "tsc -p tsconfig.json && rm -rf skills && cp -R ../../skills skills && chmod +x dist/main.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageskills/live-comments/SKILL.md:16 · npx invocation of non-well-known package — may execute untrusted code3. **Sources.** Ask the user which tools their decisions live in, and have them run `npx live-comments connect <system>` for each one.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagpackages/cli/skills/live-comments/SKILL.md:17 · Fake instruction boundary tag…e. 4. **Authority.** Draft person definitions from `npx live-comments directory <system>` and `git log` authors, then groups and places from the teams the user describe…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagpackages/cli/skills/live-comments/SKILL.md:75 · Fake instruction boundary tag… members(linear:team/PRICING)`. Get exact ids from `npx live-comments directory <system>` rather than guessing them. Show the definition to the user and add it to `AUTH…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/AGENTS.snippet.md:6 · npx invocation of non-well-known package — may execute untrusted code- If a ticket, document or file decides the rule, add `@source <ref> ["<quote>"] [by <authority>]`. Read sources only with `npx live-comments read <ref>` and copy quotes exactly from its output.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/AGENTS.snippet.md:5 · npx invocation of non-well-known package — may execute untrusted code- Before writing a business rule, run `npx live-comments context <file>:<line>`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/AGENTS.snippet.md:8 · npx invocation of non-well-known package — may execute untrusted code…ined in `AUTHORITY`. When the user says who decides, match their words against `npx live-comments authority`; if no name fits, propose a definition (with exact ids from `npx liv…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/live-comments/SKILL.md:14 · npx invocation of non-well-known package — may execute untrusted code1. Run `npx live-comments init`. It creates an empty config and `AUTHORITY` file, installs this skill and registers the MCP server. It makes no choices for the project.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagpackages/cli/skills/AGENTS.snippet.md:8 · Fake instruction boundary tag…me fits, propose a definition (with exact ids from `npx live-comments directory <system>`) and add it only after the user agrees. Otherwise reuse the names nearby code …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/live-comments/SKILL.md:14 · npx invocation of non-well-known package — may execute untrusted code1. Run `npx live-comments init`. It creates an empty config and `AUTHORITY` file, installs this skill and registers the MCP server. It makes no choices for the project.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagskills/AGENTS.snippet.md:8 · Fake instruction boundary tag…me fits, propose a definition (with exact ids from `npx live-comments directory <system>`) and add it only after the user agrees. Otherwise reuse the names nearby code …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/AGENTS.snippet.md:6 · npx invocation of non-well-known package — may execute untrusted code- If a ticket, document or file decides the rule, add `@source <ref> ["<quote>"] [by <authority>]`. Read sources only with `npx live-comments read <ref>` and copy quotes exactly from its output.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/AGENTS.snippet.md:9 · npx invocation of non-well-known package — may execute untrusted code- If a source is in a tool the project can't read yet, ask the user to run `npx live-comments connect <system>`, and write an `@open` with `in <place>` meanwhile.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/live-comments/SKILL.md:18 · npx invocation of non-well-known package — may execute untrusted code5. Add the CI step `init` printed, and run `npx live-comments check`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/live-comments/SKILL.md:17 · npx invocation of non-well-known package — may execute untrusted code…onnect <system>` for each one. 4. **Authority.** Draft person definitions from `npx live-comments directory <system>` and `git log` authors, then groups and places from the team…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/live-comments/SKILL.md:16 · npx invocation of non-well-known package — may execute untrusted code3. **Sources.** Ask the user which tools their decisions live in, and have them run `npx live-comments connect <system>` for each one.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/AGENTS.snippet.md:9 · npx invocation of non-well-known package — may execute untrusted code- If a source is in a tool the project can't read yet, ask the user to run `npx live-comments connect <system>`, and write an `@open` with `in <place>` meanwhile.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/live-comments/SKILL.md:17 · npx invocation of non-well-known package — may execute untrusted code…onnect <system>` for each one. 4. **Authority.** Draft person definitions from `npx live-comments directory <system>` and `git log` authors, then groups and places from the team…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagpackages/cli/skills/AGENTS.snippet.md:9 · Fake instruction boundary tag- If a source is in a tool the project can't read yet, ask the user to run `npx live-comments connect <system>`, and write an `@open` with `in <place>` meanwhile.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:165 · Fake instruction boundary tag · informational: not an instruction file| `directory <system>` | A connected tool's accounts and places, with exact ids |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/live-comments/SKILL.md:25 · npx invocation of non-well-known package — may execute untrusted codenpx live-comments context <file>:<line>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagpackages/cli/skills/live-comments/SKILL.md:64 · Fake instruction boundary tag- Ask the user to connect it with `npx live-comments connect <system>`. Connecting needs the user to sign in, so you can't do it for them. Tell them exactly which command to run and why.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackages/cli/src/init.ts:101 · npx invocation of non-well-known package — may execute untrusted coderun: npx live-comments check --base origin/\${{ github.base_ref || 'main' }}`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagskills/live-comments/SKILL.md:64 · Fake instruction boundary tag- Ask the user to connect it with `npx live-comments connect <system>`. Connecting needs the user to sign in, so you can't do it for them. Tell them exactly which command to run and why.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagpackages/cli/skills/live-comments/SKILL.md:16 · Fake instruction boundary tag3. **Sources.** Ask the user which tools their decisions live in, and have them run `npx live-comments connect <system>` for each one.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagskills/AGENTS.snippet.md:9 · Fake instruction boundary tag- If a source is in a tool the project can't read yet, ask the user to run `npx live-comments connect <system>`, and write an `@open` with `in <place>` meanwhile.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/AGENTS.snippet.md:5 · npx invocation of non-well-known package — may execute untrusted code- Before writing a business rule, run `npx live-comments context <file>:<line>`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/live-comments/SKILL.md:18 · npx invocation of non-well-known package — may execute untrusted code5. Add the CI step `init` printed, and run `npx live-comments check`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/AGENTS.snippet.md:8 · npx invocation of non-well-known package — may execute untrusted code…ined in `AUTHORITY`. When the user says who decides, match their words against `npx live-comments authority`; if no name fits, propose a definition (with exact ids from `npx liv…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackages/cli/skills/live-comments/SKILL.md:25 · npx invocation of non-well-known package — may execute untrusted codenpx live-comments context <file>:<line>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Fake instruction boundary tagSPEC.md:283 · Fake instruction boundary tag · informational: not an instruction file…me in the authority file, fully expanded, as JSON. | | `live-comments directory <system>` | yes | List a connected system's accounts (id, display name, email) and place…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:167 · Fake instruction boundary tag · informational: not an instruction file| `connect <system>` | Connect a tool through Composio or Nango |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagSPEC.md:284 · Fake instruction boundary tag · informational: not an instruction file…and place definitions can be written with exact ids. | | `live-comments connect <system> [--via nango\|composio] [--base-url <url>]` | yes | Connect a tool through a tr…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,298 tok
2 files · 57 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.