fable-loop
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill package does not contain any executable scripts, binaries, or active code components. It consists entirely of markdown documentation, YAML configurations, and JSON templates.
- [INDIRECT_PROMPT_INJECTION]: The skill workflow is designed to ingest and process external state information, which presents an attack surface for indirect prompt injection.
- Ingestion points: External command-line outputs, CI build statuses, and API response bodies processed during polling (SKILL.md).
- Boundary markers: The instructions recommend state classification but do not specify mandatory delimiters or 'ignore' warnings for the raw external data.
- Capability inventory: The skill is intended to manage recurring executions of external probes, including network requests and shell commands.
- Sanitization: No specific sanitization or filtering logic is provided for the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata