bc-performance
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to perform web searches and fetch documentation to guide its optimization tasks. This creates a surface for indirect prompt injection attacks if the retrieved content contains malicious instructions designed to manipulate the agent.
- Ingestion points:
WebSearchandWebFetchtools are used to ingest external data from the web as instructed inSKILL.md. - Boundary markers: Absent. The skill lacks instructions to treat external data as untrusted or to ignore embedded commands within fetched content.
- Capability inventory: The skill has access to
Bash,Write, andEdittools as defined in the frontmatter ofSKILL.md, which represents a significant impact if an injection occurs. - Sanitization: Absent. The skill does not define any validation or sanitization for data fetched from the web.
Audit Metadata