documentation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions in the 'Voice Matching Priority' section that direct the agent to prioritize user-provided transcripts or example text over all other established rules. This explicit prioritization creates a vector for prompt injection, as malicious instructions embedded in a user transcript could potentially override the agent's safety or functional constraints.\n- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection vulnerability surface by combining user data processing with file system capabilities. \n
  • Ingestion points: User-provided voice transcripts, tone guidance, and example text used for voice matching.\n
  • Boundary markers: Absent. The skill provides no instructions for using delimiters or warnings to ignore embedded commands within user content.\n
  • Capability inventory: The skill outlines a documentation workflow that involves writing files to specific paths (e.g., /path/to/docs/articles/).\n
  • Sanitization: Absent. There is no requirement for validation or filtering of user-supplied text before it is processed or written to the file system.\n- [NO_CODE]: The skill consists entirely of Markdown guidelines and metadata, with no executable scripts, binaries, or configuration files that would require code analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:55 PM