call-scorecards
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues, malicious code, or obfuscation were identified. The skill follows its stated purpose of providing sales coaching frameworks.
- [SAFE]: The skill processes user-provided transcripts, a potential surface for indirect prompt injection. However, the risk is mitigated as the skill has no capability to perform sensitive actions like file writing, network calls, or command execution.
- Ingestion points: Sales transcripts are analyzed in the 'When a transcript is supplied' section of
SKILL.md. - Boundary markers: The instructions do not specify delimiters for transcript content, relying on the agent to cite evidence from the text.
- Capability inventory: No tools with side effects (e.g., shell, network, filesystem) are requested or used.
- Sanitization: No sanitization or filtering of transcript content is performed.
Audit Metadata