atelier-grill-me
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon data from the local codebase.
- Ingestion points: The skill instructions explicitly direct the agent to 'explore the codebase', 'read the files', and use tools like 'grep' to answer its own questions before asking the user (File: SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters, XML tags, or explicit system instructions to ignore or treat embedded commands within those files as untrusted data.
- Capability inventory: The skill possesses the capability to write to the filesystem, specifically to create Architecture Decision Records (ADRs) in
docs/adr/and to append durable choices to a journal file at.claude/LESSONS.md(File: SKILL.md). - Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the codebase before it is used to influence the agent's logic or the content of the files it writes.
Audit Metadata