competitor-social-research

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data retrieved from social media platforms.
  • Ingestion points: The scrapecreators-api and comment-mining tools ingest posts, transcripts, and audience reactions from external sources into the agent context (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or clear boundaries for the external content.
  • Capability inventory: The skill is scoped to analysis, labeling, and report generation; it does not invoke shell commands or perform file writes (SKILL.md, skill.meta.json).
  • Sanitization: No explicit content sanitization or filtering is described.
  • [SAFE]: The skill uses specialized research tools (scrapecreators-api, outlier-post-finder, etc.) that are consistent with its stated purpose of social media intelligence. All interactions are focused on gathering public content for competitive research.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 02:23 PM
Security Audit — agent-trust-hub — competitor-social-research