Search Documentation
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted user queries and external data to synthesize answers. In Phase 4 (Synthesis), the LLM reads article content retrieved from an external store, which could contain malicious instructions designed to manipulate the agent's behavior.\n
- Ingestion points: The
queryinput parameter inSKILL.mdand documentation content retrieved via thesearch_docsaction.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands used when the agent processes retrieved documentation content.\n
- Capability inventory: The skill utilizes the
crmcapability and executes searches via thesearch_docsinternal tool.\n - Sanitization: No sanitization is performed on documentation text before it is presented to the LLM for synthesis, although keyword extraction is used for the search phase.
Audit Metadata