plan-importer
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local CLI commands (e.g., 'planweave init', 'planweave paths', and 'planweave validate') to resolve workspace paths and verify the integrity of plan packages. This is standard operational behavior for integrating with the specified tool.
- [PROMPT_INJECTION]: The skill processes untrusted external content such as READMEs, ADRs, and issues, creating a surface for indirect prompt injection. 1. Ingestion points: Document sources including README, ADRs, issues, and specs are ingested as described in the Import Workflow section of SKILL.md. 2. Boundary markers: SKILL.md does not specify the use of delimiters or instructions to ignore embedded commands within the source data. 3. Capability inventory: The skill allows shell command execution through the CLI and file writes to the project workspace (referenced in Command Entry and Workspace sections of SKILL.md). 4. Sanitization: The skill employs validation commands and a 'Plan Quality Gate' to verify the logic and schema of the generated plan files.
Audit Metadata