product-self-knowledge
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of standard instructional markdown to guide agent self-introspection. No malicious patterns, unauthorized data access, or obfuscation were detected.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest data from repo files and workbench state. However, this is necessary for its primary purpose of providing accurate system information. 1. Ingestion points: Repo files, package metadata, and workbench state. 2. Boundary markers: None explicitly defined. 3. Capability inventory: Ability to read local files and verify command/resource discovery. 4. Sanitization: No specific sanitization or filtering of ingested data is mentioned.
Audit Metadata