workflow-new-content
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 (scripts/dfs_client.py, scripts/schema_gen.py, scripts/indexnow.py, and scripts/report_publish.py) to perform data analysis, generate SEO schema, and produce client reports.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves fetching and processing data from external search results and competitor pages, which creates an attack surface where untrusted content could influence the agent's instructions.
- Ingestion points: The skill fetches the top 5 ranking competitor pages using webfetch and extracts 'People Also Ask' questions from search engines.
- Boundary markers: The instructions do not define boundary markers or provide specific directives to the agent to ignore potentially malicious instructions embedded within the fetched web content.
- Capability inventory: The skill possesses capabilities to write files to the local filesystem (CONTENT-BRIEF-*.md), create directories, and perform network requests via the provided scripts.
- Sanitization: No explicit sanitization, validation, or filtering of external web content is mentioned before the data is processed by the agent.
Audit Metadata