project-analyzer

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from the user's project, including README and schema files, which constitutes a surface for indirect prompt injection.\n
  • Ingestion points: Reads various local manifest and documentation files such as package.json, pyproject.toml, README.md, CLAUDE.md, and database schema files.\n
  • Boundary markers: Not present; the skill instructions do not specify the use of delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded within the ingested files.\n
  • Capability inventory: The skill is restricted to read-only file system operations using tools like Read, Glob, Grep, and restricted Bash commands; it does not request network access or the ability to modify files.\n
  • Sanitization: No sanitization or validation logic is defined for the content extracted from user project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 12:35 AM
Security Audit — agent-trust-hub — project-analyzer