research
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it instructs the agent to ingest data from untrusted external primary sources (e.g., APIs, source code, documentation) and write results to the repository. \n
- Ingestion points: External sources mentioned in SKILL.md. \n
- Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are provided. \n
- Capability inventory: File writing to the repository. \n
- Sanitization: Absent; no validation of external content is specified. \n- [NO_CODE]: The skill consists entirely of natural language instructions and configuration metadata, containing no scripts or executable binaries.
Audit Metadata