deslop
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of markdown instructions and does not include any scripts, executables, or external dependencies.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted code data from the current workspace.
- Ingestion points: Processes recently modified code from the current session's workspace as instructed in SKILL.md.
- Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands within processed files are defined.
- Capability inventory: The skill assumes an environment where the agent has file-system read and write access to perform code modifications.
- Sanitization: Absent; no sanitization or validation logic is specified for the input data.
Audit Metadata