fnl-coordinator-sessions
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes several external and potentially untrusted files to coordinate work, which creates an attack surface for instructions embedded in data.
- Ingestion points: Reads from
spec.md,plan.md,tasks.md,AGENTS.md, and processes external git diffs and test outputs (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the ingested files.
- Capability inventory: The skill is authorized to edit artifacts, perform git commits, create worktrees, and start/manage new agent sessions.
- Sanitization: There is no mention of sanitization or validation of the content read from the external files before it is used to influence agent behavior.
- [COMMAND_EXECUTION]: The skill instructions include explicit shell commands for the agent or user to execute.
- Evidence: Instructions to run
npx skills add finolabs/finolabs-vibecode --skill fnl-delegateif dependencies are missing. - Context: Mentions creating git worktrees and managing automated session starts, which involves direct interaction with the system shell.
Audit Metadata