grokipedia-recommendations
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains internal instructions for the agent to modify its output depth based on session history, which is considered a standard operational instruction.
- [PROMPT_INJECTION]: The skill facilitates processing user-provided content through templates. Ingestion points: User input for topics and URLs in SKILL.md. Boundary markers: Uses placeholders like [Topic] but lacks strict delimiters. Capability inventory: Only text generation is supported; no file system or network access is available. Sanitization: No content validation is performed. The risk remains safe due to the low capability tier.
Audit Metadata