seo-checklist-generator
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple local Python scripts to perform its functions:
python scripts/project_memory.py: Used to load site type and competitor data fromseo-project.yml.python scripts/dfs_client.py: Used to query ranking data for a target domain.python scripts/report_publish.py: Used to generate branded HTML and PDF reports from markdown files.- [INDIRECT_PROMPT_INJECTION]: The skill processes external configuration data which creates a surface for indirect prompt injection attacks.
- Ingestion points: Data is ingested from
seo-project.ymlinSKILL.md(Step 1 of Process). - Boundary markers: There are no boundary markers or instructions telling the agent to ignore potential instructions embedded within the
seo-project.ymlfile or the output ofproject_memory.py. - Capability inventory: The skill has the ability to execute shell commands (via Python scripts) and write files (
CHECKLIST-...) to the local filesystem. - Sanitization: The skill lacks any description of sanitization, validation, or escaping of the data retrieved from project memory before it is used to generate the checklist.
Audit Metadata