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, andreprise.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, creatingassets/files, andqa-<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