design-high-level
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external requirement documents to generate high-level design sections. If a requirements document contains malicious instructions, the agent might follow them during the generation process. However, the skill's lack of high-privilege capabilities restricts the potential impact.
- Ingestion points:
Docs/requirements/(referenced in SKILL.md) - Boundary markers: Absent; the skill does not define specific delimiters for external content.
- Capability inventory: File system write access to
Docs/designs/andDocs/In-Progress/for saving HLD documents. - Sanitization: Absent; no explicit instructions are provided to the agent to sanitize or ignore instructions embedded within the source requirements files.
Audit Metadata