ask-nova
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external workflow definitions to guide its decision-making process.
- Ingestion points: Reads content from
skills/using-skills/SKILL.md,skills/using-design-skills/SKILL.md, andskills/using-workflows/SKILL.md(or~/.agents/skills/equivalents). - Boundary markers: The instructions do not define delimiters or specific markers to isolate the content of these files from the agent's core instructions, increasing the risk that instructions embedded in the workflow files could be obeyed.
- Capability inventory: The skill is limited to file reading and text-based interaction with the user. It does not perform network operations, execute shell commands, or write to the filesystem.
- Sanitization: There is no mention of sanitizing or validating the ingested content before it is used to influence the agent's recommendation.
Audit Metadata