autonomous-agent-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its intended purpose of codebase assessment through local file discovery. It uses a Python script (
scripts/discover.py) to identify common project configuration files (CI/CD, containers, testing, dependencies) and provides recommendations based on a set of criteria. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external codebases, which serves as an ingestion point for untrusted data. This finding is assessed as safe given the skill's purpose and limited capabilities.
- Ingestion points: The
scripts/discover.pyscript reads directory structures and file content previews (up to 50 lines) from the target project. - Boundary markers: No explicit delimiters or boundary markers are implemented in the discovery script.
- Capability inventory: The skill possesses local file read capabilities via the provided Python script.
- Sanitization: The discovery script employs basic safety measures such as truncating file previews and ignoring encoding errors to prevent ingestion of excessively large or malformed files.
Audit Metadata