to-task
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and reconcile task ledger data from a project repository, which is a surface for indirect prompt injection. If an attacker embeds malicious instructions within a task ledger file, the agent could potentially be influenced by them while performing its reconciliation tasks.
- Ingestion points: The skill reads task definitions and status from repository ledger files like references/task-ledger.md and project-specific durable ledgers.
- Boundary markers: No specific delimiters or boundary markers are defined to isolate or identify untrusted ledger content within the prompt context.
- Capability inventory: The skill restricts the agent from implementing code, mutating Git, or executing commands, which significantly mitigates the potential impact of any successful injection.
- Sanitization: There is no evidence of sanitization or input validation mechanisms in the instructions.
Audit Metadata