define-my-content-pillars

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill is a set of markdown-based instructions for the agent to help a user with content strategy. It contains no executable scripts, system-level file access, or hardcoded credentials.- [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it instructs the agent to ingest and analyze 'ten to fifteen posts' written by the user. 1. Ingestion points: Step 1 ('Ten to fifteen posts they have already written'). 2. Boundary markers: No delimiters or explicit warnings to ignore instructions inside the posts are provided. 3. Capability inventory: The skill is limited to analysis and text generation; no 'exec', 'eval', or network exfiltration capabilities are present in the instruction set. 4. Sanitization: No steps for filtering or sanitizing the input text are defined. The risk is minimized by the lack of exploitable tools.- [EXTERNAL_DOWNLOADS]: The skill references 'voicemoat.com' as an optional external service to provide analytics and post history. This is documented as a legitimate integration for users of that external platform and does not involve automated or suspicious remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:23 AM