spec-human-decision
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it is designed to ingest, parse, and process external documentation (PRDs, Dev-plans) that may originate from untrusted sources or remote links.
- Ingestion points: The skill reads PRD and development plan content from local file paths or external URLs provided in the input arguments or context.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the documentation it processes.
- Capability inventory: The skill is capable of reading repository files, writing modifications back to PRDs and development plans, creating new decision record files (e.g.,
.decisions.md), and using interactive user-input tools. - Sanitization: The instructions do not specify any sanitization, escaping, or validation logic for the content extracted from external documents before it is used to generate prompts or update files.
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch content from external URLs when a link is provided as a target for documentation review. This is an intended functional capability for processing remote PRDs and development plans.
Audit Metadata