ponytail
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as task descriptions and existing source code, which could contain embedded malicious instructions.
- Ingestion points: The agent is instructed to read the task and the code it touches (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions that might be present within the data being processed.
- Capability inventory: The agent has the capability to write, modify, and delete code, and execute grep commands on the codebase.
- Sanitization: There is no mention of sanitizing or validating the input data before processing.
Audit Metadata