gsd-validate-phase
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by design.
- Ingestion points: Untrusted data enters via the
{{GSD_ARGS}}parameter and by reading existing project artifacts likeVALIDATION.mdandSUMMARY.md(mentioned in theobjectiveandprocesssections ofSKILL.md). - Boundary markers: There are no explicit delimiters (e.g., XML tags or triple quotes) or negative constraints instructing the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill utilizes
spawn_agentto delegate work and performs file write operations to updateVALIDATION.md, creating a path for malicious instructions in the data to trigger unauthorized actions. - Sanitization: No sanitization, escaping, or validation logic is defined for the ingested user input or file content before it is interpolated into the workflow.
Audit Metadata