grouchygiraffe-recipe-lookup

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted data from local YAML files and image thumbnails which could contain instructions to override the agent's behavior.
  • Ingestion points: Reads uploader, handle, and description from .yaml files, and recipe names from _thumb.jpg images using vision capabilities (SKILL.md, Steps 2 & 3).
  • Boundary markers: Absent. There are no delimiters or warnings to ignore instructions within the processed files.
  • Capability inventory: The agent has access to file reading, WebSearch, and WebFetch tools (SKILL.md, Steps 2, 4, 5).
  • Sanitization: Absent. Extracted strings are used directly in subsequent steps without validation.
  • [DATA_EXFILTRATION]: Data extracted from local files is sent to external web services.
  • Evidence: The skill extracts authors' names, handles, and recipe titles from local files and uses them as search queries in WebSearch, effectively sending local metadata to a third-party search engine (SKILL.md, Steps 4 & 5).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 02:32 AM
Security Audit — agent-trust-hub — grouchygiraffe-recipe-lookup