content-repurposer

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content (articles, blog posts, transcripts) provided by users in 'Phase 0: Intake'.
  • Ingestion points: SKILL.md (Phase 0: Intake).
  • Boundary markers: Absent. There are no instructions or delimiters to isolate user-provided content from the skill's directives.
  • Capability inventory: None. The skill is documented as 'Pure reasoning' and does not request any tools, network access, or file system modifications.
  • Sanitization: Absent. No filtering or input validation is performed on the source content.
  • [NO_CODE]: This skill consists entirely of natural language instructions and metadata. It includes no scripts, binaries, or other executable components.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — content-repurposer