pm-market-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data such as market rules, source claims, and resolver details, which presents an attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through external sources, claims, and market rules described in the 'Workflow' section of SKILL.md (Step 3) and section 5 of references/pm-market-analysis-reference.md.
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore' warnings for the external content ingested during the analysis process.
- Capability inventory: While the skill primarily focuses on data analysis and structured output, the agent's default tools (such as network access and file system interaction) are available to act on processed information.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external URLs or source claims before interpolation into the analysis prompt.
Audit Metadata