The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process data from external websites.
Ingestion points: The skill uses WebSearch and WebFetch to gather information for writing chapters (found in SKILL.md under MODES OF OPERATION).
Boundary markers: There are no instructions for using delimiters or boundary markers to separate external data from the agent's execution context.
Capability inventory: The skill is authorized to use Write, Edit, and Bash tools, providing a significant impact surface if the agent obeys instructions hidden in external data.
Sanitization: No sanitization or validation protocols for the external content are specified in the instructions.
[COMMAND_EXECUTION]: The skill directs the agent to execute a local Python script to perform automated style checks.
Evidence: The instruction python3 skills/writer/scripts/lint.py <file> --aeo in SKILL.md triggers the execution of a script located in a relative path within the workspace. While intended for linting, the execution of local scripts is a capability that requires user awareness.

essay-write