sales-social-listening

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation and configuration files from the official sales-skills GitHub organization to ensure accurate recommendations when routing to related platform-specific skills.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from fetched files and local learning files to guide its responses, creating an indirect prompt injection surface. 1. Ingestion points: WebFetch from the sales-skills GitHub repository and reading the local references/learnings.md file. 2. Boundary markers: Absent. 3. Capability inventory: The skill is primarily advisory and lacks high-risk capabilities like arbitrary command execution or sensitive file exfiltration. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 11:36 PM
Security Audit — agent-trust-hub — sales-social-listening