aiox-validate-story-draft
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill treats the contents of internal project files as the primary source of operational instructions, which creates a vulnerability surface.
- Ingestion points: The skill loads instructions from
.aiox-core/development/tasks/validate-next-story.mdand processes user-provided content at{story-path}. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its hardcoded logic and potentially malicious instructions embedded within the story files or task files.
- Capability inventory: The skill has permissions to read and write files on the local disk and append to logs.
- Sanitization: There is no evidence of validation or sanitization of the content loaded from the task files before the agent executes the logic contained within them.
- [DYNAMIC_EXECUTION]: The skill implements a pattern where it 'loads and executes' instructions from a local markdown file (
.aiox-core/development/tasks/validate-next-story.md) at runtime. - This 'Task SOT' (Source of Truth) approach means the skill's actual behavior is determined by external data rather than static instructions in
SKILL.md. - While the files are local, this mechanism bypasses static analysis of the skill itself by deferring logic to external files.
Audit Metadata