analyze-skill
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
bunx cc-skills-usagecommand to gather metrics, session data, and invocation logs.- [EXTERNAL_DOWNLOADS]: Usingbunxto runcc-skills-usageinvolves fetching the package from the npm registry, which is a standard method for executing Node.js utilities.- [PROMPT_INJECTION]: The skill ingests and analyzes raw user messages from historical conversation logs to identify missed trigger patterns, creating an indirect prompt injection surface. - Ingestion points: User messages and trigger phrases are retrieved via the
bunxcommand output (Step 1). - Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within the ingested conversation data.
- Capability inventory: The skill has access to shell execution (
bunx) and local file reading (~/.claude/skills/). - Sanitization: No sanitization or escaping is performed on the historical message content before analysis.
Audit Metadata