social-media-manager

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides strategic guidance and content planning tools. All logic is contained within the instructions and a local Python script using only standard libraries. No signs of prompt injection, obfuscation, or malicious intent were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for local brand context but lacks high-privilege capabilities to exploit it.
  • Ingestion points: The skill reads brand voice and audience data from marketing-context.md (SKILL.md).
  • Boundary markers: Not present.
  • Capability inventory: The skill is limited to providing strategic advice and generating text-based calendar artifacts; it does not have network access or file-writing permissions.
  • Sanitization: Content is utilized as instructional context for strategy formulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — social-media-manager