python-quality-audit
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and analyze untrusted data from source code files, pull requests, and git diffs. This architecture creates a surface for indirect prompt injection, where malicious instructions hidden in code comments or documentation could attempt to manipulate the audit report or the behavior of the specialized analysis agents.
- Ingestion points: The skill reads Python source files, git diff outputs, and pull request data as part of its defined scope resolution (SKILL.md).
- Boundary markers: Although the skill uses independent analysis lanes for separation, it lacks explicit instructions to treat the ingested code as data only or to use boundary markers (delimiters) to prevent the agent from obeying embedded instructions.
- Capability inventory: The skill possesses broad file-read access across the repository and dispatches multiple agents to evaluate the content.
- Sanitization: No sanitization or escaping of the input source code is defined before it is analyzed by the language model agents.
Audit Metadata