vibe-check
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted third-party application code, which is a potential vector for indirect prompt injection.\n
- Ingestion points: The agent is instructed to load and analyze repository files (e.g.,
package.json,supabase/migrations,.env,master.key,config/credentials) to perform its audit.\n - Boundary markers: The
SKILL.mdfile contains a 'Ground rules' section explicitly instructing the agent to treat repository contents as data, not instructions, and to ignore any content attempting to modify its task or verdict.\n - Capability inventory: The skill's capabilities are limited to reading repository files and generating a structured JSON report. There are no provisions for network access, arbitrary command execution, or writing to the file system.\n
- Sanitization: The skill includes mandatory rules to avoid printing secrets and provides a template for fix suggestions that the user can review before applying.
Audit Metadata