security-best-practices
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and analyze untrusted project source code.
- Ingestion points: SKILL.md directs the agent to inspect the repository and pay attention to instructions in project documentation or prompt files.
- Boundary markers: Absent. The skill lacks delimiters or instructions to ignore malicious prompts embedded in the code being analyzed.
- Capability inventory: The agent can write report files, modify source code, and perform git commits as specified in SKILL.md.
- Sanitization: Absent. There are no instructions to sanitize or validate content from the repository.
- Risk factor: The 'Overrides' section in SKILL.md explicitly instructs the agent to follow instructions in the project's documentation that may bypass security best practices, which an attacker could exploit to mislead the agent.
Audit Metadata