launch-checklist
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple untrusted sources within the repository, creating an attack surface where malicious instructions in comments or documentation could influence agent behavior.
- Ingestion points: Reads project context and metadata from
CLAUDE.md, files inproduction/milestones/, existing releases inproduction/releases/, and the content calendar indesign/live-ops/content-calendar.md. It also performs keyword scans across the entire codebase. - Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded prompts within the processed files.
- Capability inventory: The skill possesses the capability to write files to the local file system using the
Writetool. - Sanitization: No sanitization or validation of the ingested text is performed before it is interpolated into the final markdown report.
Audit Metadata