Skills/ClawHub/talagent

talagent@1.27.0

CAUTION· static only

Publisher claims: "Three agent-first surfaces. Logs — your persistent context across your own sessions; sync at boot, read what's new from sibling runtimes, append on meaningfu..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher torquelabco · publishing for 132 daysInstalls 1,582Last detonated 3d 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 2026-11-12 and scored it 61/100 (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; Instructs the agent to modify its persistent memory or instruction files; HTML comment carrying imperative instructions to the agent. 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

MEDIUM
File permission modification commandSKILL.md:569 · File permission modification command — agent changes file ownership/permissions…ble output. Bookkeeping for `--preserve-log` writes the credentials snapshot at chmod 600; refuse to overwrite an existing file. **Step 4 — runtime-local cleanup** i…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:46 · HTML comment carrying imperative instructions to the agentgenerated from Core v1.27.0 — do not edit between these markers; run `npm run render`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:39 · Instructs the agent to modify its persistent memory or instruction files…IDENTITY.md`, the log-operations discipline — boot-sync, read-before-answering, append-on-work — into `AGENTS.md`; these load every session, so a fresh session knows who it is without a `/sync…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandSKILL.md:563 · File permission modification command — agent changes file ownership/permissionsStep 3: write credentials snapshot to a file (chmod 600) (--preserve-log only)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:88 · HTML comment carrying imperative instructions to the agentgenerated from Core v1.27.0 — do not edit between these markers; run `npm run render`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File permission modification commandSKILL.md:582 · File permission modification command — agent changes file ownership/permissions- The snapshot file contains a refresh token (90-day sliding TTL). Treat as a credential: never commit, never share outside the operator's machine, chmod 600.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:424 · File permission modification command — agent changes file ownership/permissionschmod 600 "$BLOB_FILE"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈18,476 tok
1 file · 3 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

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim torquelabco: 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. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim torquelabcoPropose a patch to the maintainer