serp-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes shell commands using local Python scripts (
scripts/dfs_client.py,scripts/project_memory.py,scripts/report_publish.py) with parameters derived directly from user input, such as<query>,<user-domain>, and<report>.md. This pattern presents a potential risk if the underlying execution environment does not properly sanitize these arguments. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content retrieved from search results and web pages.
- Ingestion points: The skill instructions specify fetching the top 3 organic results and processing data from the
dfs_client.pySERP payload inSKILL.md. - Boundary markers: No specific delimiters or instructions are used to distinguish external data from the skill's logic or to prevent the agent from following instructions embedded in the search results.
- Capability inventory: The skill has access to shell execution for local scripts and network capabilities for web fetching.
- Sanitization: There is no mention of sanitization, filtering, or validation of the fetched web content before it is processed by the agent.
Audit Metadata