seo-roadmap-builder
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes several local Python scripts to perform its core functions.
- Evidence: Instructions to run
python scripts/project_memory.py,python scripts/dfs_client.py,python scripts/google_client.py, andpython scripts/report_publish.pyfor data retrieval and report formatting. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external audit reports, creating a surface for injection attacks.
- Ingestion points: Input described in
SKILL.mdas "audit findings (or a prior report file)". - Boundary markers: None identified; the agent is instructed to "collect every open finding/recommendation" without isolation instructions.
- Capability inventory: The skill can execute local scripts and write files to paths determined by the
SEO_REPORTS_DIRenvironment variable. - Sanitization: No sanitization or validation of the audit finding content is mentioned before processing or inclusion in output files.
Audit Metadata