scanning-for-vulnerabilities
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external codebases and dependencies, which represents a potential attack surface where malicious code or comments could attempt to influence agent behavior.
- Ingestion points: The
scripts/scan.pyscript recursively iterates through and reads files within a user-provided directory usingpathlib.Path.rglob. - Boundary markers: The instructions and script do not implement specific delimiters or warnings to prevent the agent from following instructions embedded in the scanned files.
- Capability inventory: The skill has broad tool permissions, including
Bash(cmd:*),Read,Write, andEditas specified in the frontmatter. - Sanitization: There is no logic in the provided scripts to sanitize or validate the content of the files before processing.
Audit Metadata