content-distribution

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content (blog posts, articles, transcripts) to generate distribution plans and derivative assets. This represents an attack surface where instructions embedded within the processed content could influence agent behavior.
  • Ingestion points: The agent ingests user-provided long-form content during Phase 1 (Content Atomization) as described in SKILL.md.
  • Boundary markers: None explicitly defined in the prompts to differentiate between the agent's core instructions and the source content provided for atomization.
  • Capability inventory: The skill uses a local script scripts/check-output.py to validate deliverables and instructs the agent to create new markdown files based on templates/output-template.md.
  • Sanitization: There is no evidence of sanitization or filtering of the source content before it is processed for atomization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 12:46 PM
Security Audit — agent-trust-hub — content-distribution