social-selling

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves researching prospect profiles, posts, and comments to personalize outreach. This process ingests external, untrusted content into the agent's context.
  • Ingestion points: Prospect LinkedIn profiles, activity feeds, and engagement lists (likers/commenters) referenced in SKILL.md and references/b2b-influencer-measurement.md.
  • Boundary markers: The instructions lack explicit delimiters or guidance for the agent to ignore instructions embedded within the analyzed social media content.
  • Capability inventory: The skill includes a local Python script (scripts/check-output.py) for deliverable validation and assumes the agent has access to web research tools.
  • Sanitization: No sanitization or filtering logic is specified for the data retrieved during the research process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:04 AM
Security Audit — agent-trust-hub — social-selling