deslopify
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform mechanical scans by executing shell commands such as
grep,tr,sed, andawkagainst user-provided text files (e.g.,draft.txt). Specific command templates are provided inreferences/tells.md(sections 5 and 6) and invoked inSKILL.mdPhase 1. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill accepts and processes untrusted text provided by the user in the conversation or via local files.
- Boundary markers: The instructions do not define delimiters or explicit 'ignore embedded instructions' warnings for the shell command execution phase.
- Capability inventory: The skill utilizes shell command execution (subprocess calls to Unix utilities) to process untrusted data.
- Sanitization: There is no explicit requirement for the agent to sanitize, escape, or validate user-controlled content before it is interpolated into shell commands.
Audit Metadata