task-explainer-html
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a protocol for ingesting task-related data via an XML-like structure ().
- Ingestion points: Data enters through the block in the mission dispatch, involving fields like work, parent, decision, and fact.
- Boundary markers: Uses explicit XML tags and a strict line-oriented format to isolate data fields.
- Capability inventory: Modifies the artifacts/explainer.html file and uses the ha task CLI for supplemental data retrieval.
- Sanitization: Explicitly mandates XML entity escaping (e.g., &, <) and parsing rules to prevent injection and ensure deterministic processing.
- [SAFE]: The skill includes security-conscious design requirements, such as a 'leaks grep' self-check and a mandate for JavaScript-free HTML output, which mitigates potential browser-based attack vectors.
Audit Metadata