media-writer

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is entirely comprised of Markdown files containing documentation and writing advice. No scripts, binaries, or automated tasks are included.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied technical content, creating a potential surface for indirect prompt injection. However, the lack of dangerous capabilities makes this surface non-exploitable.\n
  • Ingestion points: The skill accepts generic technical content from the user (SKILL.md).\n
  • Boundary markers: Absent; no specific delimiters or ignore instructions are provided to the agent for the input content.\n
  • Capability inventory: None; the skill is limited to text transformation and has no access to sensitive tools or shell commands.\n
  • Sanitization: Absent; no input filtering is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:14 PM
Security Audit — agent-trust-hub — media-writer