keyword-research
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (
scripts/dfs_client.pyandscripts/report_publish.py) with user-supplied arguments to fetch SEO data and generate reports. This relies on the agent's ability to run shell commands in the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via the output of
scripts/dfs_client.py, which fetches keyword ideas, related terms, and SERP features from the DataForSEO API. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded in the API response data.
- Capability inventory: The skill uses
bashto execute Python scripts, performs file writes to the local file system (KEYWORDS-<topic>-<date>.md), and invokes a reporting script. - Sanitization: There is no mention of sanitization or validation of the data retrieved from the external API before it is processed or stored.
Audit Metadata