testimonial-harvester
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process raw customer feedback and comments, which are untrusted data sources.
- Ingestion points: Processes raw comments and customer proof as described in README.md and SKILL.md.
- Boundary markers: Absent. The instructions lack explicit delimiters or guidance for the agent to disregard embedded commands in the raw data.
- Capability inventory: Specified in SKILL.md; the agent has access to Read and Write tools, allowing file system interaction.
- Sanitization: Absent. No input validation or filtering is defined for the external content.
Audit Metadata