The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process content from external websites and search engines, creating a surface for indirect prompt injection attacks.
Ingestion points: The skill uses tavily/search-assistant, exa/search, and tavily/extract to pull data from the web into the agent's context (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or specific system instructions to ignore potential commands embedded in the retrieved competitive data.
Capability inventory: The skill allows for file writing (markdown reports), image processing (infsh/stitch-images), and Python execution (infsh/python-executor).
Sanitization: There is no evidence of sanitization or filtering of the external search content before it is interpolated into the analysis templates.
[DYNAMIC_EXECUTION]: The skill employs dynamic Python execution to generate visual deliverables.
Evidence: The 'Positioning Map' section includes a Python script using matplotlib which is executed via the infsh/python-executor app. While the script provided is a static template, it involves the execution of code within the agent environment at runtime.

competitor-teardown