The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and analyzes content from arbitrary external websites.
Ingestion points: The extract_page_content function in SKILL.md fetches text content from external URLs returned by search results.
Boundary markers: There are no instructions or delimiters defined to isolate the fetched external content from the agent's core instructions.
Capability inventory: The skill has network-read capabilities via requests.get and file-write capabilities via the cat shell command.
Sanitization: There is no evidence of sanitization or filtering of the fetched HTML/text content before it is passed to the agent for synthesis.
[EXTERNAL_DOWNLOADS]: Fetches search data from the Brave Search API and retrieves content from third-party websites for research purposes.
[COMMAND_EXECUTION]: Employs the cat command to save synthesized research reports to the local filesystem.

web-research