app-recommender

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow that ingests and processes data from the app-scanner tool, which could contain untrusted data.
  • Ingestion points: List of installed applications retrieved from the app-scanner tool (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious commands within the application list.
  • Capability inventory: The skill is documentation-only and contains no internal scripts, subprocess calls, or network operations.
  • Sanitization: There is no explicit requirement for the agent to sanitize or validate the application names before processing them.
  • [NO_CODE]: The skill consists entirely of Markdown instructions and metadata; no scripts or executable files are included or referenced for execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:56 PM
Security Audit — agent-trust-hub — app-recommender