write-research-spec
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a textual transformation tool for converting research briefs into executable plan specifications and does not utilize any potentially dangerous capabilities such as subprocess execution, network utilities, or file system writing.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user which represents a theoretical surface for injection, though it lacks the capabilities to perform dangerous actions or exfiltrate data.
- Ingestion points: Ingests
confirmed_north_star,research_brief, anduser_constraintsas defined inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or guardrails to ignore embedded commands within the input data.
- Capability inventory: None; the skill is limited to text generation and plan drafting without access to shell, network, or file system tools.
- Sanitization: No explicit validation or sanitization of input content is implemented.
Audit Metadata