app-brief
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read external specification files or links from a 'specs/' directory to populate the app brief. (1) Ingestion points: Files or links provided by the user within the project's specification folder. (2) Boundary markers: Not present in the instruction template. (3) Capability inventory: Writing to local documentation files (BRIEF.md, STORIES.md, SPEC.md) and triggering subsequent development skills (new-mac-app, user-stories). (4) Sanitization: Not explicitly defined; the skill relies on the agent's internal safety protocols for processing untrusted text.
- [SAFE]: The skill performs routine documentation and project planning tasks. It does not execute dangerous shell commands, access sensitive system credentials, or perform unauthorized network exfiltration. The use of local file paths and the prompt-based interview format are standard and safe behaviors.
Audit Metadata