prowler-compliance-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted compliance JSON data provided in Pull Requests.\n
- Ingestion points: Compliance JSON files parsed in
validate_compliance.pyand referenced inSKILL.mdshell templates.\n - Boundary markers: Absent; the skill does not define clear delimiters or instructions to the agent to disregard instructions embedded within the compliance data.\n
- Capability inventory: The skill allows the use of
Bash,Write,Edit, andWebFetchtools, which could be exploited if an injection is successful.\n - Sanitization: The
validate_compliance.pyscript validates JSON structure and check ID existence but does not sanitize text fields (Description, Rationale, etc.) for malicious prompt instructions.
Audit Metadata