editorial-quality-gate
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation includes examples of shell commands for validating the skill's integrity using local python scripts.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted external content such as news briefs and article drafts.
- Ingestion points: Content provided by the user for editorial review (SKILL.md).
- Boundary markers: Instructions explicitly tell the agent to scan for 'prompt residue' and 'internal editorial instructions'.
- Capability inventory: The skill is restricted to analyzing text and generating reports using a provided template.
- Sanitization: The instructions include a specific 'Non-Negotiables' section that requires blocking prompt residue and meta-commentary from public output.
Audit Metadata