flow-plan

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a vulnerability surface for indirect prompt injection as it processes untrusted technical specifications and project files to generate technical tasks and commit messages.
  • Ingestion points: The skill is instructed to read external project data including ticket.md, reprise.md, technical specifications, and existing project source code (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious content embedded within the specifications it reads.
  • Capability inventory: The skill has the capability to write new files to the .task/ directory and facilitates the execution of downstream tasks through other skills like flow-build.
  • Sanitization: There are no explicit sanitization or validation steps mentioned for the data ingested from project files before they are used to influence the planning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 08:04 AM
Security Audit — agent-trust-hub — flow-plan