data-lineage-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data pipeline contexts and requirements to generate code and configurations, creating a surface for injection attacks.\n
- Ingestion points: Processes user requests and external data pipeline descriptions as described in SKILL.md.\n
- Boundary markers: Absent; no delimiters or instructions are provided to the agent to ignore embedded commands in the data being processed.\n
- Capability inventory: The skill allows the agent to use powerful tools including Read, Write, Edit, Grep, and arbitrary shell command execution via Bash(cmd:*).\n
- Sanitization: Absent; no explicit validation or escaping of external content is mentioned.\n- [METADATA_POISONING]: The skill uses the excessively broad keyword "data" as an activation trigger in its description. This may cause the skill to automatically activate for a wide range of generic data-related queries that are not specific to the skill's intended purpose of tracking data lineage tracker operations.
Audit Metadata