The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/dfs_client.py and scripts/report_publish.py) via the bash shell to retrieve search engine results and generate final reports. While these appear to be internal tools, executing commands based on external data (like report filenames) requires careful handling.
[INDIRECT_PROMPT_INJECTION]: The skill fetches content from the top 5 organic search results and user-provided URLs using the webfetch tool. This external content is then processed to extract entities and build a consensus set. Maliciously crafted content on these external pages could attempt to influence the agent's behavior.
Ingestion points: Content retrieved from external URLs via the webfetch tool as described in the 'Process' section.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the untrusted web content from the agent's core instructions.
Capability inventory: The skill has the ability to execute shell commands (python scripts/...), invoke tools (webfetch), and write files to the local directory (ENTITIES-<keyword>-<date>.md).
Sanitization: There is no mention of sanitizing, filtering, or escaping the content fetched from the web before it is analyzed by the agent.

entity-extraction