python-anti-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill contains a hardcoded dummy secret within an educational code block designed to demonstrate the "Hard-Coded Configuration" anti-pattern.
- Evidence: The file
SKILL.mdcontains the lineAPI_KEY = "sk-12345"in a section explicitly labeled "BAD: Secrets and config in code". This is a non-functional placeholder used for instructional purposes. - [INDIRECT_PROMPT_INJECTION]: The skill is intended to review code provided by users, which creates an inherent surface for indirect prompt injection if that code contains hidden instructions.
- Ingestion points: User-provided Python code snippets passed to the agent for review against the checklist in
SKILL.md. - Boundary markers: The skill does not specify particular delimiters or "ignore instructions" warnings for the code it processes.
- Capability inventory: The skill's YAML frontmatter does not request access to high-risk tools (such as network access, file system writes, or shell execution), limiting the potential impact of an injection.
- Sanitization: There are no defined mechanisms for sanitizing or filtering the content of the code being reviewed.
Audit Metadata