weekly-monthly-report
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
findcommand to programmatically discover directories and files matching specific report periods. This is a standard operational requirement for the skill's primary function. - [PROMPT_INJECTION]: The skill processes untrusted data from multiple external documents, which presents a surface for indirect prompt injection.
- Ingestion points: The skill reads all files within user-specified or automatically discovered directories (Markdown, DOCX, TXT, PDF).
- Boundary markers: The instructions do not define specific delimiters to separate ingested document text from the agent's internal instructions.
- Capability inventory: Local file system discovery using
find, file reading, and content aggregation into a final report. - Sanitization: No specific sanitization, validation, or filtering logic is defined for the content extracted from the source documents.
Audit Metadata