The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data provided via the $ARGUMENTS variable to conduct a report review.
Ingestion points: The $ARGUMENTS placeholder in SKILL.md captures external user-provided document content.
Boundary markers: The skill does not utilize delimiters or specific instructions to isolate the document content from the session logic.
Capability inventory: The skill triggers a /report-coaching session.
Sanitization: No sanitization or validation of the input content is observed in the skill instructions.
[NO_CODE]: The skill contains no executable scripts, binaries, or source code files, consisting only of the SKILL.md instruction file.

report-review