masterplan
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data (project briefs and existing repository files) to generate implementation plans. This creates a surface where adversarial instructions embedded in documentation or source code could influence the agent's planning logic or subsequent implementation tasks.
- Ingestion points: Reads project briefs from chat or disk and inspects existing files within the repository as defined in the 'Workflow' section of
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the ingested materials.
- Capability inventory: The skill performs file system read operations across the repository and file system write operations to the
docs/plans/directory. - Sanitization: There are no documented mechanisms for sanitizing or validating the content of the briefs or source files before processing them into a plan.
Audit Metadata