gs-deslop
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes git diffs from external branches, which are untrusted sources. This creates a surface where an attacker could embed instructions within the code or comments of a branch to influence the agent's behavior.
- Ingestion points: The skill reads the 'diff against main' to identify code for removal or modification.
- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the skill definition.
- Capability inventory: The skill has the capability to modify or delete code within the project files based on its interpretation of the diff.
- Sanitization: There is no evidence of sanitization or filtering to prevent the agent from following instructions embedded in the processed diffs.
Audit Metadata