engagement-routine

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is advisory, providing strategic guidance and drafting social media content without executing system commands, accessing sensitive files, or making network requests.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from external files.
  • Ingestion points: Reads brand-profile.md and social-strategy.md in Step 0 to determine engagement parameters.
  • Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands within the ingested files.
  • Capability inventory: No dangerous capabilities such as subprocess execution, file writing, or network operations are present in the analyzed files.
  • Sanitization: No validation or sanitization of the content from the ingested files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:27 PM
Security Audit — agent-trust-hub — engagement-routine