blueprint
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's 'Research' phase involves reading project structure, existing plans, and memory files to gather context for plan generation. This data ingestion surface is vulnerable to indirect prompt injection if project files contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads local project files, existing plans, and memory files during the first phase of its pipeline (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined in the skill to treat ingested content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill has the capability to read and write files to the filesystem (specifically the
plans/directory) and utilize git/gh CLI tools if available (SKILL.md, Phases 3 and 5). - Sanitization: The skill does not mention any sanitization, filtering, or validation of the content read from the project environment before it is interpolated into the design and drafting phases.
Audit Metadata