sitrep
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the repository environment (git logs, diffs, and the
TASKS.mdfile) to generate reports. This creates a surface for indirect instructions to influence the agent's summary or subagent behavior.\n - Ingestion points: Git logs, status, diffs, and the
TASKS.mdfile (SKILL.md).\n - Boundary markers: None defined for separating data from instructions.\n
- Capability inventory: Subprocess execution (
git,gh) and subagent orchestration (SKILL.md).\n - Sanitization: No content sanitization is described.\n- [COMMAND_EXECUTION]: The skill executes shell commands to inspect the repository.\n
- Evidence: Standard git commands (
git status,git log,git diff) are used for evidence gathering (SKILL.md).
Audit Metadata