aiox-review-story
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting instructions and data from external files that could contain malicious directives.
- Ingestion points: Reads task-specific instructions from
.aiox-core/development/tasks/qa-gate.mdand the story file provided via arguments. - Boundary markers: The protocol lacks explicit boundary markers or instructions to treat ingested content as untrusted data.
- Capability inventory: The skill performs file system writes to
docs/qa/gates/and modifies the content of story files based on the review outcome. - Sanitization: No sanitization or validation of the content retrieved from external task definitions or story files is performed.
- [NO_CODE]: The skill consists entirely of markdown instructions without accompanying executable scripts or binaries.
Audit Metadata