knowledge-graph-enhancement
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell command templates to fetch data (e.g.,
python scripts/dfs_client.py serp --keyword "<brand>"). If the user-provided<brand>input contains shell metacharacters and is not properly sanitized by the agent platform before execution, it could lead to command or argument injection. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external web sources to perform brand notability assessments.
- Ingestion points: Data is pulled from external sources using
scripts/dfs_client.py mentions,scripts/dfs_client.py content, and thewebfetchtool. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the fetched web content.
- Capability inventory: The skill has the capability to write files to the local file system (
KG-<brand>-<date>.md) and execute Python scripts via subprocess calls. - Sanitization: There is no mention of sanitizing or escaping the external content before it is processed by the agent for analysis.
Audit Metadata