ponytail-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze untrusted external data, such as code diffs, pull request content, and source files, creating an attack surface where embedded instructions could influence the agent's behavior.
- Ingestion points: The skill reads uncommitted changes, staged changes, specific branches, PR links, and file contents as described in the 'Understand first' section of SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or use 'ignore instructions' warnings when processing code content.
- Capability inventory: The skill is primarily read-oriented and the instructions specify it 'changes no code', which limits the potential for automated damage, though the reviewer persona provides influential feedback.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the ingested code content before it is processed by the agent.
Audit Metadata