data-quality
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a companion check routine that instructs the agent to run
lscommands on specific local directories, such as~/.claude/skills/and~/.agent/skills/, to determine if recommended companion skills are already installed. - [EXTERNAL_DOWNLOADS]: The skill recommends the installation of additional components from the vendor's own repository using
npx skills add AbsolutelySkilled/AbsolutelySkilled, which is consistent with its role as a developer utility. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and process external data, such as SQL queries and YAML contract specifications.
- Ingestion points: YAML contract files in
references/data-contracts-spec.mdand SQL transformation logic inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided code examples.
- Capability inventory: The skill has the capacity to execute shell commands (via the dependency check) and perform network operations (via OpenLineage and DataHub emitters).
- Sanitization: The provided examples do not include logic for sanitizing or validating the content of the data files before processing.
Audit Metadata