ponytail-audit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted repository content, including README files and source code, to perform its analysis. This creates a surface where a maliciously crafted repository could attempt to influence the agent's audit results through embedded instructions.
- Ingestion points: All files within the targeted repository (e.g., README.md, build configurations, source code).
- Boundary markers: None. There are no instructions to use delimiters or specifically ignore instructions found in data.
- Capability inventory: Reading local files and generating text-based audit reports.
- Sanitization: The skill does not specify any sanitization or validation of the code content before it is processed.
Audit Metadata