chatgpt-citation-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits and processes external web content, which is a common attack vector for indirect prompt injection. * Ingestion points: Fetches robots.txt and target web pages using webfetch tools. * Boundary markers: There are no explicit instructions to the agent to ignore or delimit potentially malicious instructions within the fetched web content. * Capability inventory: The skill has the ability to write reports to the local file system and execute Python scripts (scripts/dfs_client.py and scripts/report_publish.py). * Sanitization: No sanitization or validation of the external web content is mentioned.
- [COMMAND_EXECUTION]: The skill executes local Python scripts with parameters derived from user-provided inputs like brand names and core topics. * Evidence: Uses
python scripts/dfs_client.pyfor baseline mentions andpython scripts/report_publish.pyfor final report formatting.
Audit Metadata