analyst
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (scan results) and user-supplied input ($ARGUMENTS), creating a potential vector for indirect instructions.
- Ingestion points: Data enters the context via the synthesis of 'available scan results' and the interpolation of '$ARGUMENTS' into the report title.
- Boundary markers: No delimiters (e.g., XML tags or clear separators) or 'ignore' instructions are present to prevent the agent from following commands embedded in the results.
- Capability inventory: The skill is restricted to text synthesis; it contains no executable code, network operations, or file-writing capabilities.
- Sanitization: The input data is not sanitized or filtered before being processed by the agent.
Audit Metadata