restriction-of-processing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data subject requests, which are externally controlled inputs. This creates a potential surface for indirect prompt injection if the agent processes malicious instructions embedded within a request.\n
- Ingestion points: Request data is handled in SKILL.md (Step 1) and processed via the
scripts/process.pyscript (e.g., parameters for subject-id, ground, and data-categories).\n - Boundary markers: The instructions in SKILL.md and workflows.md lack specific delimiters or instructions to ignore embedded commands within the processed data requests.\n
- Capability inventory: The skill uses a local Python script (
scripts/process.py) to structure metadata. It does not perform network operations or access sensitive system files, which limits the potential impact of an injection.\n - Sanitization: The provided script utilizes
argparsewith predefined choices for thegroundandpurposefields, providing a degree of input validation for specific parameters, but no sanitization is applied to free-text fields like justification or subject ID.
Audit Metadata