Skills/ClawHub/agency-os

agency-os@1.0.0

CAUTION· static only

Publisher claims: "Manage and mutate Notion-based agency task and corpus data via slash commands using medium-reasoning Sonnet subagent for accurate dispatch board updates." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher automatelab · publishing for 189 daysInstalls 895Last detonated 2 h ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-14 and scored it 58/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentreferences/general-guidance.md:54 · HTML comment carrying imperative instructions to the agentTODO: fill in your project root, docs, skills, and credential locations. Example: - Project root: `C:\Work\my-project` - Docs: `docs/` - Skills: `.claude/skillsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandSKILL.md:104 · Process kill command — agent can terminate processes/agency-os kill <id> [--reason "..."]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:778 · Process kill command — agent can terminate processes| "kill X" / "drop X" / "X is no longer relevant" | `kill <id>` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:476 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…lter (Notion API version `2025-09-03`). The integration token (`NOTION_KEY` in `.env`) must be shared with the Tasks database. Run: ``` python .claude/skills…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandSKILL.md:121 · Process kill command — agent can terminate processes…, "approve that", "make weekly task recurring", "mark X done with link <url>", "kill the Y idea" — the skill mutates Notion the same way it would for the slash comma…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:685 · Process kill command — agent can terminate processes## Command: `kill <id> [--reason "..."]`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:486 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files1. Loads `NOTION_KEY` from `.env` and `tasks_database.data_source_id` from `references/notion-pointers.json`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/query-tasks.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE = REPO_ROOT / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈12,176 tok
1 file · 9 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.

What would make this Verified

22 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim automatelab: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim automatelabPropose a patch to the maintainer