wecomcli-sheet
Warn
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/recalc.pycontains functionality to compile an embedded C source shim at runtime usinggcc. This compiled library is then injected into thesoffice(LibreOffice) process using theLD_PRELOADenvironment variable. This mechanism is intended to shim socket-related system calls to enable communication in restricted sandbox environments whereAF_UNIXsockets are blocked.\n- [COMMAND_EXECUTION]: The skill performs shell command execution viasubprocess.runinscripts/recalc.pyto invokegcc,soffice, and timeout utilities (timeout/gtimeout).\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes data from external spreadsheet files, creating a vulnerability surface where malicious instructions embedded in cells could be processed by the agent.\n - Ingestion points: Untrusted data is ingested from local
.xlsx,.xlsm,.xls,.csv, and.tsvfiles viascripts/collect.py.\n - Boundary markers: While
SKILL.mdincludes safety instructions for the agent to ignore commands within processed data, there are no programmatic boundary markers or delimiters enforced on the data passed to the prompt.\n - Capability inventory: The skill has the capability to write to local and online files, execute shell commands, and modify spreadsheet structures.\n
- Sanitization: No programmatic sanitization or filtering is performed on the cell values before they are analyzed by the agent.
Audit Metadata