security-compliance-auditor
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/audit.shto perform security scans. The script is well-structured, uses safe file handling patterns (find -print0), and performs read-only operations such as grep and npm audit. - [PROMPT_INJECTION]: The skill ingests untrusted data from local files, creating a surface for indirect prompt injection. This is a common characteristic of auditing tools that process user-controlled content.
- Ingestion points: The
scripts/audit.shscript reads various source files (Python, JS, YAML, etc.) in a user-specified directory. - Boundary markers: None present; the script outputs raw matches directly to the agent's context without delimiters or instructions to ignore embedded prompts.
- Capability inventory: The skill executes its own script which performs file system reads and runs
npm audit. - Sanitization: No sanitization or escaping is performed on the data read from files before it is processed by the agent.
Audit Metadata