social-content
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown documentation and templates. A review of all files found no evidence of prompt injection, credential harvesting, or unauthorized network operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill framework in
references/reverse-engineering.mdencourages the analysis of large quantities of scraped social media posts to identify viral patterns.\n - Ingestion points: External content from LinkedIn, Twitter/X, and other platforms provided by the user to the agent for pattern analysis.\n
- Boundary markers: The skill does not provide specific instructions or markers to distinguish between legitimate data and potential embedded instructions in the analyzed posts.\n
- Capability inventory: The skill possesses no internal capabilities for command execution, file writing, or network access; it functions purely as an instructional guide.\n
- Sanitization: There are no instructions for sanitizing or filtering input from scraped social media data, as the agent is intended to analyze the text content directly.
Audit Metadata