The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API which could theoretically contain malicious instructions.
Ingestion points: Data is fetched from https://www.guidetopharmacology.org/services using the requests library across multiple functions in SKILL.md (e.g., find_target, target_interactions, ligand_structure).
Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands within the pharmacological data.
Capability inventory: The skill performs network reads (requests.get) and file system writes (df.to_csv) using the pandas library.
Sanitization: The skill uses pd.to_numeric(..., errors="coerce") to handle affinity strings, which provides basic data type validation but not full content sanitization.

gtopdb-database