ponytail-audit
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository, including READMEs, configuration files, and source code. This creates an attack surface where malicious instructions embedded in the codebase (e.g., in comments or strings) could attempt to influence the agent's analysis or output.
- Ingestion points: Files within the analyzed repository (SKILL.md).
- Boundary markers: None identified in the prompt to separate repository content from instructions.
- Capability inventory: Analysis and reporting (the prompt specifies it is a one-shot report that changes nothing, suggesting no write or network capabilities are requested).
- Sanitization: No input sanitization or specific instruction to ignore embedded prompts is present.
Audit Metadata