deslop
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze and modify code diffs and branch content. This creates an ingestion point for untrusted data that could potentially contain adversarial instructions. However, the skill lacks the necessary capabilities to perform sensitive operations like network exfiltration or shell execution, limiting the impact of potential injections.\n
- Ingestion points: Code diffs relative to the main branch as described in SKILL.md.\n
- Boundary markers: None provided to distinguish code from instructions.\n
- Capability inventory: No scripts or tool-based capabilities are defined within the skill package.\n
- Sanitization: No input validation or sanitization logic is present.\n- [NO_CODE]: The skill contains only a markdown instruction file and does not include any scripts, libraries, or binaries that would require runtime execution.
Audit Metadata