first-plan-lens-engine
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is local filesystem inspection to categorize software projects based on common manifest files (e.g., package.json, go.mod).\n- [COMMAND_EXECUTION]: The skill implements a detection algorithm using filesystem metadata and file content patterns but does not execute external shell commands or arbitrary code.\n- [DATA_EXFILTRATION]: No network calls, external downloads, or exfiltration patterns were identified. The skill's output is restricted to creating local documentation within a .first-plan/ directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill analyzes data from external codebase manifests to determine the project type.\n
- Ingestion points: File contents of manifest files (like package.json, go.mod, Cargo.toml) in the analyzed project (SKILL.md).\n
- Boundary markers: None explicitly defined in the logic.\n
- Capability inventory: Local file reading and writing (restricted to project files and the .first-plan/ topology directory) and the invocation of other local lens skills.\n
- Sanitization: The skill uses a hardcoded mapping table to route stacks, which prevents arbitrary content from the manifests from being used as execution paths.
Audit Metadata