gsd-reapply-patches
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the content of local patch files and metadata during the merge process, which presents a surface where instructions embedded in the data could influence the agent's behavior.
- Ingestion points: Reads
backup-meta.jsonand file content from the{{PLATFORM_ROOT}}/gsd-local-patchesdirectory (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the content being compared and merged.
- Capability inventory: The skill utilizes
Read,Write,Edit, andBashtools (SKILL.md). - Sanitization: No explicit content sanitization or validation is described; the agent is instructed to identify and apply modifications based on the file contents.
Audit Metadata