sales-call-review
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted sales call transcripts provided by the user.
- Ingestion points: External transcripts are provided by users via paste or file attachment to be analyzed (SKILL.md, Workflow).
- Boundary markers: The skill implements a "Transcript gate" to assess data quality and an "Evidence rule" that mandates verbatim transcript quotes for every scoring decision, which forces the agent to focus on specific data points (SKILL.md, Transcript gate, Evidence rule).
- Capability inventory: The skill possesses no capabilities for network requests, file system modification, or command execution; its output is restricted to generating text reviews.
- Sanitization: The skill relies on the agent's internal safety protocols and the defined rubric structure to process content safely, though no explicit algorithmic sanitization of transcript text is performed.
- [SAFE]: The skill follows secure instruction practices, provides clear references for its methodology, and includes detailed evaluation cases to ensure consistent and safe performance without side effects.
Audit Metadata