The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process academic papers, which constitute untrusted external data.
Ingestion points: The agent reads paper drafts and reviewer comments provided by the user as part of the orchestration process in SKILL.md.
Capability inventory: The skill allows the use of high-privilege tools including Bash, Write, Edit, WebSearch, and WebFetch as defined in the frontmatter.
Boundary markers: The instructions lack explicit delimiters or specific 'ignore embedded instructions' warnings for the data being processed, which may allow malicious instructions inside a paper to influence agent behavior.
Sanitization: There is no mention of sanitization, escaping, or filtering logic for the content of the papers or reviewer comments before they are processed by the agent or delegated to other skills.

paper-workflow