harness-accept
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple local shell scripts (
scripts/load-cross-project-groups.sh,scripts/accept-past-issues.sh,scripts/render-html.sh, andscripts/plan-brief-open.sh) to process project data and generate reports. These scripts are managed as part of the local project environment. - [COMMAND_EXECUTION]: Standard CLI utilities such as
git,sha256sum, andawkare used to resolve the project name and generate identifying hashes for data retrieval. - [SAFE]: The skill ingests data from local memory searches (MCP) and script outputs. It utilizes a structured JSON schema (
acceptance-context.v1) as a boundary for data processing. Capabilities are limited to local filesystem writes and bash script execution. A redaction flag (--with-redaction) is used for cross-project data retrieval to minimize exposure risks. - [PROMPT_INJECTION]: Instructions are focused on task execution and do not contain patterns designed to bypass agent constraints or safety guidelines.
Audit Metadata