forge-plan
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes project-specific documentation, creating a surface for indirect prompt injection. This is inherent to the skill's primary function of PRD generation. \n
- Ingestion points: The skill reads content from documentation files
docs/analysis.mdanddocs/prd.md. \n - Boundary markers: No specific delimiters or instructions are used to isolate or ignore potentially malicious content from these files. \n
- Capability inventory: The skill executes
forge-memoryCLI commands and performs file write operations todocs/prd.md. \n - Sanitization: Content from the ingested files is processed without validation or sanitization. \n- [COMMAND_EXECUTION]: The skill executes the
forge-memoryutility (search, log, consolidate, sync) for state management and logging. These commands are local to the Forge environment provided by the author and represent standard functionality.
Audit Metadata