search-intent-analysis
Warn
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts (
scripts/dfs_client.pyandscripts/report_publish.py) using bash to fetch SERP data and publish reports. - [DYNAMIC_EXECUTION]: The instructions for the agent involve interpolating user-supplied keywords directly into shell command templates (e.g.,
python scripts/dfs_client.py serp --keyword "<keyword>"). This pattern is susceptible to command injection if a malicious user provides a keyword containing shell operators like;,&&, or|. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted user input.
- Ingestion points: User-provided keywords and location/language settings in
SKILL.md. - Boundary markers: None are defined to separate user input from the command logic or file content.
- Capability inventory: Execution of shell commands via Python scripts and file creation/writing to the local filesystem.
- Sanitization: There are no instructions provided to validate or sanitize the keywords before they are passed to the shell or written to the report files.
Audit Metadata