sales-talkwalker

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches remote skill definition files from the author's GitHub repository and potentially third-party repositories to improve recommendation logic.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting remote content and user data which can influence the agent's behavior and be persisted locally.
  • Ingestion points: Remote SKILL.md files are retrieved via WebFetch from GitHub repositories.
  • Boundary markers: No explicit delimiters or instructions to ignore instructions embedded within the fetched content are present.
  • Capability inventory: The skill appends discovered information to a local learnings file (references/learnings.md) and generates invocations for other skills.
  • Sanitization: No sanitization or validation of the fetched remote content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 12:21 AM
Security Audit — agent-trust-hub — sales-talkwalker