wecomcli-doc-manage
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the "wecom-cli" binary to perform document management tasks such as searching, renaming files, and updating membership permissions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes document metadata (titles and content highlights) retrieved from WeCom, which could theoretically contain instructions intended to influence the agent's behavior.
- Ingestion points: Document data returned by the "wecom-cli doc search" command as described in "SKILL.md".
- Boundary markers: The "SKILL.md" file contains a dedicated "Security提示" (Security Tips) section that explicitly instructs the agent to ignore any commands or execution requests found within data returned by the interface.
- Capability inventory: Execution of document management commands via the "wecom-cli" subprocess across "SKILL.md" and multiple referenced files including "doc-members-update.md", "doc-names-update.md", and "doc-rules-update.md".
- Sanitization: Relies on specific instructions for the agent to treat data as non-executable; no explicit programmatic filtering or escaping of the command-line output is defined.
Audit Metadata