competitive-research-snapshot
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its reliance on external data.
- Ingestion points: The workflow gathers data from external sources including competitor websites, review sites, and news releases as specified in the 'Application' section of SKILL.md.
- Boundary markers: The skill employs a labeling system (Fact/Inference/Assumption) which helps the agent distinguish between source content and its own reasoning, although it lacks technical delimiters.
- Capability inventory: The skill is designed to perform searches and generate comparative snapshots.
- Sanitization: It implements an 'Evidence quality' metric and requires citations for all findings to ensure data integrity.
Audit Metadata