flow-build

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from project-related files which can influence agent behavior.
  • Ingestion points: The skill is instructed to read content from ticket.md, project specifications, plans, journals, and reprise.md (SKILL.md).
  • Boundary markers: There are no instructions to use specific delimiters or protective warnings when reading these external files.
  • Capability inventory: The skill has the capability to write to the file system (e.g., updating ticket.md, creating assets/ files, and qa-<sujet>.md), perform Git commits, and execute shell commands for tests and database operations.
  • Sanitization: No sanitization or validation steps are defined for the data ingested from tickets or specifications before they are processed or used to generate commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 08:04 AM
Security Audit — agent-trust-hub — flow-build