implement-plan
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow implementation plans, tickets, and repository instructions from the local filesystem. These external inputs are treated as sources for the task list and verification steps, which could contain malicious instructions.
- Ingestion points:
SKILL.md(Step 1: 'Read the approved plan or tickets', 'read each file'). - Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within these data sources.
- Capability inventory: The agent is authorized to modify files and execute project-specific commands, including builds and verification tests (
SKILL.mdStep 3 & 4). - Sanitization: No sanitization or content validation of the plans or tickets is required by the workflow.
- [COMMAND_EXECUTION]: The workflow involves executing project-defined verification commands and build processes. This capability is necessary for implementation but could be abused if a malicious plan specifies harmful commands as part of the 'verification' or 'build' process.
Audit Metadata