datasheets
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/datasheet_page_selector.pyutilizessubprocess.runto callpdfinfoandpdftotextfor PDF metadata and text extraction. These calls are implemented using argument lists rather than shell strings, which prevents command injection vulnerabilities via PDF file paths. - [DATA_EXFILTRATION]: No network-related functions or external data transfer mechanisms were found. The skill operates entirely within the project's local filesystem to manage its extraction cache.
- [PROMPT_INJECTION]: The skill's instructions in
SKILL.mdand reference guides focus solely on technical extraction logic and do not contain instructions aimed at overriding agent behavior or bypassing safety filters. - [CREDENTIALS_UNSAFE]: No hardcoded API keys, secrets, or attempts to access sensitive system directories (such as
.ssh,.aws, or.envfiles) were identified in the source code or documentation.
Audit Metadata