init
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration behaviors were detected. The skill operates within the expected parameters of a developer workflow tool.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
canonandorchestracommands. These are used specifically for interacting with the local project store and database, following the platform's standard operating procedures. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data (e.g.,
README.md,git log) to generate project metadata. This attack surface is mitigated by explicit instructions to treat this data as proposals and to obtain human confirmation before any records are finalized in the database.
Audit Metadata