social-content

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a 'Reverse Engineering' framework that involves ingesting and analyzing large datasets (500-1000+ posts) from external social media platforms.
  • Ingestion points: External content from social media platforms (LinkedIn, Twitter/X, etc.) gathered via manual collection or third-party scraping tools (e.g., Apify, Phantom Buster).
  • Boundary markers: The skill does not provide instructions for the agent to use delimiters or ignore potential instructions embedded within the processed external data.
  • Capability inventory: The agent is tasked with qualitative analysis, emotional trigger extraction, and pattern codification from the raw text of these external posts.
  • Sanitization: There are no requirements defined for filtering or sanitizing the external content before it is processed by the agent.
  • [NO_CODE]: The skill consists entirely of markdown-based instructions, personas, and templates. It does not include any scripts, package dependencies, or dynamic command execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 08:51 AM
Security Audit — agent-trust-hub — social-content