grimoire-spec

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content, including Architecture Decision Records (ADRs) and existing requirement documents, to generate new specifications. This ingestion surface could be exploited if those files contain malicious instructions aimed at influencing the agent's output.
  • Ingestion points: Reads repository surfaces, ADR files, and requirement source paths as instructed in SKILL.md.
  • Boundary markers: Uses a specific Markdown template (spec-template.md) to structure the generated content.
  • Capability inventory: Writing Markdown files to the .grimoire/spec/ directory.
  • Sanitization: The instructions do not specify any validation or sanitization of the ingested repository content before it is used to build the specification.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 11:06 AM