ooad-discover

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external project files such as CONTEXT.md and docs/agents/domain.md to extract domain knowledge and project context. This creates a surface for indirect prompt injection if those files contain adversarial content.
  • Ingestion points: SKILL.md specifies reading docs/agents/workflow.md, docs/agents/domain.md, and CONTEXT.md during the 'Explore' phase.
  • Boundary markers: There are no explicit instructions to the agent to treat these files as untrusted or to use delimiters.
  • Capability inventory: The skill involves reading and writing markdown files and interacting with GitHub issues via the gh CLI.
  • Sanitization: The process does not describe sanitization steps for data read from the repository.
  • [EXTERNAL_DOWNLOADS]: The templates/c4.puml file contains a remote include directive for PlantUML definitions.
  • Evidence: !include https://raw.githubusercontent.com/plantuml-stdlib/C4-PlantUML/master/C4_Context.puml.
  • Context: This is a reference to a well-known community-maintained library for C4 diagrams and is documented as a standard external resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:14 PM
Security Audit — agent-trust-hub — ooad-discover