repurpose-linkedin

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No evidence of malicious intent or dangerous capabilities was found. The skill operates within expected parameters for a content repurposing utility.\n- [PROMPT_INJECTION]: The skill processes untrusted external data (content atoms), which presents a standard surface for indirect prompt injection. However, given the primary function of generating markdown content, the risk is negligible.\n
  • Ingestion points: Processes 'content atoms' received from the orchestrator in SKILL.md.\n
  • Boundary markers: None present; the skill does not use specific delimiters to isolate user-provided text.\n
  • Capability inventory: Writes generated content to local files (e.g., linkedin/post.md, linkedin/carousel.md, linkedin/poll.md).\n
  • Sanitization: No explicit input validation or escaping mechanisms are implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:19 PM
Security Audit — agent-trust-hub — repurpose-linkedin