The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data via the $ARGUMENTS placeholder, which is passed to the slop-cleaner agent. This creates a vulnerability surface where malicious instructions embedded in the target data could potentially influence the agent's behavior.
Ingestion points: SKILL.md (via the $ARGUMENTS variable).
Boundary markers: Absent; the skill does not use delimiters or provide instructions to ignore prompts within the processed content.
Capability inventory: SKILL.md identifies the use of a slop-cleaner agent intended to modify or remove content, implying file write or edit capabilities.
Sanitization: Absent; no validation, escaping, or filtering of the input data is performed.
[NO_CODE]: The skill contains no scripts or binary executables, consisting entirely of markdown instructions and metadata.

clean-slop