seo-project-planner
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes multiple local Python scripts to perform its core functions, including data collection and report generation.
- Evidence: The skill executes
python scripts/project_memory.py,python scripts/dfs_client.py, andpython scripts/report_publish.pyusing arguments derived from user input. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from target domains which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Data is retrieved from target domains and homepages via
dfs_client.pyand incorporated into project plans. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its internal instructions and the data fetched from external SEO targets.
- Capability inventory: The skill has the ability to execute shell commands via local scripts and perform file system write operations for project plans and YAML memory files.
- Sanitization: No sanitization or validation steps are defined for external input variables like
<domain>or<homepage>before they are used in script execution or report contents.
Audit Metadata