customer-service-excellence
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves processing untrusted customer data (e.g., verbatim words and public channel posts). This data is interpolated into the agent's context during the 'Required Inputs' phase without explicit sanitization or boundary markers. However, the risk is mitigated by explicit instructions requiring adherence to structured recovery loops and strict authority ceilings.
- Ingestion points: 'The customer's words (verbatim where possible)' in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: None (instructional markdown only).
- Sanitization: None specified.
- [NO_CODE]: The skill contains no executable scripts, binaries, or automated installation processes, consisting entirely of reference and guidance documentation.
Audit Metadata