identifying-competitors
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites (via url_extraction) and web search results, which could contain malicious instructions.
- Ingestion points: The skill reads data from user-provided websites (Step 3) and external search result snippets (Step 4).
- Boundary markers: There are no instructions to use delimiters or ignore potential commands within the fetched content.
- Capability inventory: The skill has file-write capabilities (writing to
./supercmo-company/competitors.md) and network access (performing further web searches and social research). - Sanitization: No sanitization or validation logic is specified for the data retrieved from external sources before it is processed or stored.
Audit Metadata