hsdd-spec
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted documents to generate system specifications, which creates an attack surface for indirect prompt injection.
- Ingestion points: Reads PRDs, RFCs, design docs, and tickets (SKILL.md, Step 1).
- Boundary markers: Lacks explicit delimiters or instructions to ignore embedded commands within the ingested sources.
- Capability inventory: The skill creates and writes multiple markdown files to the "hsdd/spec/" directory, which are then processed by other skills in the HSDD workflow.
- Sanitization: No evidence of sanitization or filtering for the content extracted from external sources.
- [DYNAMIC_EXECUTION]: The skill's established conventions include the execution of local scripts to manage the HSDD registry.
- Evidence: The convention template explicitly instructs the execution of "node hsdd/scripts/gen-registry.mjs" (templates/conventions.md).
- Risk: While standard for development tools, the reliance on external script execution for core functionality is a dynamic behavior that depends on the integrity of the local scripts.
Audit Metadata