init-project-rules
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration, or unauthorized credential access were detected. The skill's operations are confined to the local project environment.
- [COMMAND_EXECUTION]: Uses common directory listing and file system discovery tools (ls, tree) to identify project components and configuration files for analysis.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading untrusted project files to inform documentation generation.
- Ingestion points: Reads content from files such as package.json, pom.xml, and README.md (SKILL.md, Step 1).
- Boundary markers: Absent.
- Capability inventory: Has the ability to create or modify local documentation files including AGENTS.md and bridge files (SKILL.md, Step 3, 4).
- Sanitization: Absent.
Audit Metadata