The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of code and writing samples to identify and remove AI-generated 'slop'. This creates a potential surface for indirect prompt injection if the ingested content contains hidden instructions designed to manipulate the agent's behavior.
Ingestion points: The skill instructions in SKILL.md specify inspecting staged, unstaged, committed, and untracked task files, as well as supplied text or documents.
Boundary markers: No explicit boundary markers or 'ignore' instructions for embedded data are defined in the provided skill content.
Capability inventory: The skill does not include any executable scripts or tools; it relies on the agent's native capabilities to read files and rewrite text.
Sanitization: No sanitization or validation of the input content is specified beyond the stylistic rules for rewriting.

remove-slop