llm-wiki-team-rollout
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions involve analyzing external organizational data (incident history, support channels, pull request history) to generate planning documents. This creates an indirect prompt injection surface where maliciously crafted data in those sources could potentially influence the agent's logic or output recommendations.\n
- Ingestion points:
SKILL.mdidentifies existing documentation, ADRs, onboarding material, issue/PR history, incident history, and support channels as inputs.\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded instructions for processed data.\n
- Capability inventory: The skill is compatible with coding agents with access to document workspaces and repositories.\n
- Sanitization: No explicit content filtering or sanitization steps are defined for the ingested data.\n- [NO_CODE]: The skill consists exclusively of Markdown documentation, configuration templates (YAML), and architectural diagrams. It does not include executable scripts, binaries, or automated installation logic.
Audit Metadata