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, and scripts/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, and awk are 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
Risk Level
SAFE
Analyzed
May 16, 2026, 05:19 PM
Security Audit — agent-trust-hub — harness-accept