product-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting untrusted data from multiple external sources, creating an attack surface for indirect prompt injection. 1. Ingestion points: Processes data from support tickets, app reviews, community posts, NPS comments, sales call notes, and competitor changelogs (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the data ingestion process. 3. Capability inventory: No scripts or tools are defined in the provided file; actions are performed by referenced agents (SKILL.md). 4. Sanitization: No methods for sanitizing, validating, or filtering external content are specified.
- [NO_CODE]: The skill consists entirely of descriptive markdown and instructions without any executable scripts or configuration files.
Audit Metadata