ponytail-audit
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to scan and process the entire codebase, which could contain maliciously crafted instructions designed to influence the agent's behavior.\n
- Ingestion points: Repository tree files and source code as described in SKILL.md.\n
- Boundary markers: The skill does not include instructions to delimit or ignore instructions found within the data being processed.\n
- Capability inventory: The skill's scope is restricted to generating a report and does not include capabilities for file modification or network communication.\n
- Sanitization: No sanitization or input validation for processed file content is mentioned.
Audit Metadata