skill-gap
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate workforce analysis by reading local codebase files and package manifests. It does not perform network operations to untrusted domains or execute remote scripts.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and analyze untrusted codebase content and external labor market data.
- Ingestion points: Reads the target codebase and integration manifests as specified in the 'System Discovery' phase.
- Boundary markers: The instructions do not define clear delimiters or escape sequences to separate codebase content from the agent's internal reasoning.
- Capability inventory: The agent has permissions to create directories and write analysis reports to 'docs/skill-gap-analysis.md' and append telemetry to '~/.claude/projects/skill-telemetry.md'.
- Sanitization: No explicit sanitization of codebase content is mentioned before it is processed by the LLM.
- [COMMAND_EXECUTION]: The skill includes a persistence mechanism for telemetry logging that writes to a file outside the immediate project scope.
- Evidence: The 'Self-Evolution Telemetry' section instructs the agent to append execution metadata to '~/.claude/projects/skill-telemetry.md' if the directory exists. This is a standard logging behavior for this platform and does not involve malicious command execution.
Audit Metadata