sherpy-cli
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download the tool from the vendor's repository on GitHub. These downloads are associated with the skill author's infrastructure and are necessary for the skill's operation.
- [COMMAND_EXECUTION]: The skill uses shell commands to install the CLI tool and to perform document validation and conversion tasks.
- [PRIVILEGE_ESCALATION]: The documentation includes the use of
sudofor installing the compiled binary into the system path. - [INDIRECT_PROMPT_INJECTION]: The skill processes YAML data into Markdown format, creating a surface for indirect prompt injection if input documents are untrusted. The skill documentation specifically identifies built-in security features, such as Markdown character escaping and HTML encoding, designed to mitigate these risks.
- Evidence Chain:
- Ingestion points: YAML document processing in SKILL.md.
- Boundary markers: The tool claims to escape markdown characters and encode HTML entities.
- Capability inventory: Shell command execution for tool logic.
- Sanitization: Mentioned as a core feature in the security section of the skill documentation.
Audit Metadata