Skills
skills/erichowens/some_claude_skills/recovery-social-features/Gen Agent Trust Hub

recovery-social-features

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill defines features for processing user-generated messages and recovery check-ins, which creates a potential surface for indirect prompt injection attacks.
  • Ingestion points: User-provided content in references/messaging.md (messaging system) and references/accountability.md (daily check-ins).
  • Boundary markers: The templates do not currently define explicit delimiters or instructions to ignore embedded commands in user data.
  • Capability inventory: The agent is granted access to sensitive tools including Bash, Write, and Edit as listed in SKILL.md.
  • Sanitization: The skill includes basic client-side keyword filtering for crisis detection in references/messaging.md and a template for integrating an external moderation API in references/moderation.md.
  • [EXTERNAL_DOWNLOADS]: The useContentModeration hook in references/moderation.md is configured to make a network request to an external placeholder service at https://your-moderation-worker.workers.dev to evaluate message content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:17 PM