ad-buyer-group-mapper
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized system access was identified in the skill instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied evidence such as call notes and reviews, creating an indirect prompt injection surface.
- Ingestion points: Data sources including customer call recordings, interview notes, and review mining as mentioned in SKILL.md.
- Boundary markers: The skill does not prescribe specific delimiters or instruction-bypass warnings for input data.
- Capability inventory: The skill is restricted to generating text strategies; it lacks access to commands for network or file system manipulation.
- Sanitization: No sanitization or filtering methods are defined for the evidence data sources.
Audit Metadata