integrate-other-perspectives
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied viewpoints, creating a surface for indirect prompt injection.\n
- Ingestion points: User input is ingested via the
$ARGUMENTSvariable inSKILL.md.\n - Boundary markers: The instructions do not use delimiters or explicit warnings to separate user data from the agent's logic.\n
- Capability inventory: The skill is restricted to text synthesis and does not invoke external tools, network requests, or file system operations.\n
- Sanitization: No input validation or filtering is applied to the integrated text.\n- [EXTERNAL_DOWNLOADS]: The README documentation provides installation instructions that reference the author's GitHub repository for fetching skill files.
Audit Metadata