call-summary
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely composed of instructions in SKILL.md. No executable scripts, binaries, or additional configuration files are present in the package.
- [PROMPT_INJECTION]: The skill processes untrusted external data, creating an indirect prompt injection surface.
- Ingestion points: Untrusted call notes and transcripts are ingested through the $ARGUMENTS variable and the @$1 file reference in SKILL.md.
- Boundary markers: No explicit delimiters (such as XML tags or unique dividers) or instructions are used to distinguish external data from the skill's core logic.
- Capability inventory: The skill is authorized to use Read, Glob, and Grep tools.
- Sanitization: No input validation, filtering, or sanitization is performed on the ingested text.
- [SAFE]: The skill's behavior matches its stated purpose. While it references external integrations (CRM, Gong, Email) in its documentation, these are presented as optional capabilities dependent on platform connectors. No malicious patterns, exfiltration, or obfuscation were detected.
Audit Metadata