end-session
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including Git commit messages, GitHub issue titles/bodies, and PR descriptions to generate session reports and update project boards.\n
- Ingestion points:
SKILL.md(Step 1, 3) reads fromgit log,gh issue list, andgh pr list.\n - Boundary markers: No explicit markers are used to delimit untrusted data in the generated output.\n
- Capability inventory: Extensive use of
git,ghCLI, and local file writes.\n - Sanitization:
board.mjsusesJSON.stringifyfor GraphQL variables, which prevents CLI-level injection but does not mitigate the risk of the agent following malicious instructions embedded in issue text.\n- [DYNAMIC_EXECUTION]: The skill executes shell commands that are dynamically retrieved from repository settings files located indocs/agents/*.md.\n - Evidence: Settings such as
Workspace status command,Sync with main, andDocs validationare extracted from markdown and executed as system commands.\n- [COMMAND_EXECUTION]: The skill relies on system commands (git,gh,node,bash) to manage the repository state and interact with GitHub APIs.
Audit Metadata