asc-analytics-reports
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured JSON data from external API responses via the asc CLI. Potential risks are addressed through instructions for structural parsing and strict validation of user-provided filters. Ingestion points: discovery.json and inventory.json (SKILL.md). Boundary markers: The skill mandates structural inspection and normalization of inputs. Capability inventory: Includes file system writes to temporary directories and execution of the asc, jq, and openssl utilities. Sanitization: Implements an allowlist and normalization for the granularity parameter.
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the asc tool and system utilities (jq, openssl, wc) for file management and integrity checks. All commands are purpose-built for report management and include safeguards such as checking CLI versions and help output before use.
- [SAFE]: The skill employs security best practices by utilizing umask 077 and mktemp to ensure sensitive business data is stored in isolated, restricted-access directories outside the project repository.
Audit Metadata