The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and interpret data from external files that could be controlled by a third party.
Ingestion points: SKILL.md (Step 1) specifies reading JSON/CSV files from directories such as results/ or figures/.
Boundary markers: The instructions do not define delimiters or specific boundary markers to isolate the data from the agent's control flow.
Capability inventory: The skill has access to high-privilege tools including Bash, Write, and Edit which could be abused if the agent follows instructions embedded within the experimental data.
Sanitization: There is no evidence of sanitization or schema validation for the ingested results before they are processed by the agent.

aris-analyze-results