gsd-resume-work
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external project files such as
STATE.md,CONTEXT.md, and checkpoint markers to restore session context, which represents a data ingestion surface. - Ingestion points: Mentions reading
STATE.md,CONTEXT.md, and.continue-herefiles inSKILL.md. - Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: The skill is allowed to use
Read,Bash,Write,AskUserQuestion, andSlashCommandtools. - Sanitization: No specific sanitization or validation of the file contents is described in the prompt structure.
- [SAFE]: The ingestion of state files is necessary for the skill's primary function of session restoration. The skill does not contain any obfuscated code, unauthorized network requests, or attempts to exfiltrate credentials.
Audit Metadata