competitive-enablement-refresh
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources, including existing sales enablement assets, call transcripts, and field questions from chat channels.
- Ingestion points: The workflow in SKILL.md (Steps 1 and 3) explicitly ingests existing assets, call logs, and channel messages which may contain malicious instructions.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the analyzed documents or transcripts.
- Capability inventory: The skill has the capability to generate and return artifacts (Step 10) and uses a set of tools for market intelligence, though these tools are read-only and lack high-risk execution capabilities.
- Sanitization: There is no explicit instruction to sanitize or filter input data before it is processed by the model.
Audit Metadata