write-a-adr

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a workflow that ingests untrusted data from bug reports, logs, and screenshots, which could be used to deliver indirect prompt injection attacks.
  • Ingestion points: Processes user-provided bug reports, constraints, logs, screenshots, and codebase findings (SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or explicit safety directives to ignore embedded instructions within the ingested data.
  • Capability inventory: The skill is capable of writing files to the local repository (docs/adrs/, docs/issues/) and interacting with external project management tools like GitHub or Linear (SKILL.md).
  • Sanitization: There are no specified sanitization or validation steps for external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 11:29 AM
Security Audit — agent-trust-hub — write-a-adr