fable-finish-your-turn
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill mandates autonomous task completion and error resolution, creating a vulnerability surface where the agent might execute instructions found in untrusted workspace data.
- Ingestion points: The skill processes
deliverable_state(modified files and test outputs) andturn_execution_history(SKILL.md). - Boundary markers: No delimiters or instructions to ignore embedded commands within the ingested data are defined.
- Capability inventory: The skill allows workspace mutation and the execution of diagnostic and testing commands (SKILL.md).
- Sanitization: No sanitization or validation of the content of external files or command outputs is required before processing.
Audit Metadata