bm-checkpoint
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill collects session metadata including the current username, hostname, and current working directory, which are transmitted to the
write_notetool. This collection is documented as part of the skill's purpose for creating durable work checkpoints. - [COMMAND_EXECUTION]: The skill executes Git and GitHub CLI commands (
git status,git rev-parse,gh pr view) to gather repository and pull request state. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external tool outputs to populate note content.
- Ingestion points: Data is retrieved from Git and GitHub command outputs.
- Boundary markers: No specific delimiters or safety instructions are defined for the ingested content.
- Capability inventory: The skill uses
write_notefor external storage and executes shell commands. - Sanitization: No sanitization logic is present for the data gathered from external tool outputs.
Audit Metadata