compass
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and does not include any executable scripts, command-line operations, or network exfiltration patterns. The instructions focus on logical reasoning and research synthesis.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the use of web search tools to retrieve external information, which creates an attack surface for indirect prompt injection if retrieved content contains malicious instructions.
- Ingestion points: External content fetched via the mandatory WebSearch tool in Step 3 of SKILL.md.
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the retrieved data.
- Capability inventory: The skill is limited to providing recommendations and synthesis; it contains no tools or scripts for file writing, code execution, or network egress beyond the search tool itself.
- Sanitization: No specific sanitization or filtering logic is defined for the external search results.
Audit Metadata