content-repurpose

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from user text or links to repurpose it, which introduces a potential attack surface for indirect prompt injection.\n
  • Ingestion points: User-provided text and content retrieved from external links as described in the process section (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters or specific markers to separate untrusted external data from the agent's core instructions.\n
  • Capability inventory: The skill description and process mention publishing repurposed content via 'Zernio' and 'organic-social' tools, which implies the agent has access to external write capabilities.\n
  • Sanitization: There are no instructions to sanitize, escape, or validate the ingested content before it is processed or passed to other tools.\n- [NO_CODE]: No executable scripts (Python, JavaScript), binary files, or complex command-line operations were found in the skill. The logic is entirely contained within natural language instructions, which significantly limits the direct execution attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 06:47 AM
Security Audit — agent-trust-hub — content-repurpose