competitor-discovery
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks identified. The skill's operations are consistent with its primary purpose of market research and competitor analysis.
- [PROMPT_INJECTION]: The skill processes untrusted data from external competitor websites, creating a surface for indirect prompt injection.
- Ingestion points: Step 4 instructions require the agent to fetch and extract information from discovered competitor homepages.
- Boundary markers: Absent; the skill does not provide specific instructions to the agent to delimit or ignore instructions within the fetched external content.
- Capability inventory: None detected; the skill is limited to summarizing text and presenting a ranked list, with no access to dangerous tools like subprocess execution or file system writes.
- Sanitization: Absent; there are no explicit steps for the agent to filter or validate the content retrieved from external URLs.
Audit Metadata