The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (research.py, image_search.py, image_processor.py) located in relative subdirectories (skills/deep-research/, etc.). These are internal tool calls used to gather content and process images.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it ingests data from external sources.
Ingestion points: The skill reads research.md, which is the output of a deep research script likely aggregating content from the internet.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the research data as untrusted content or to ignore potential instructions embedded within that data.
Capability inventory: The skill has access to Bash, Write, Edit, and Read tools, providing a broad capability set if the agent were manipulated by injected content.
Sanitization: There is no evidence of sanitization or validation of the content gathered during the research phase before it is interpolated into the writing process.

general-writing