The Agent Skills Directory

[SAFE]: The skill provides legitimate instructions for using a cheminformatics library. No malicious patterns such as credential theft, persistence, or privilege escalation were found.
[EXTERNAL_DOWNLOADS]: The skill instructions include installing the 'datamol' library using a standard package manager and document reading data from remote sources including S3, Google Cloud Storage, and HTTP/HTTPS. These operations are part of the library's intended functionality for data processing.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data from external sources.
Ingestion points: Data enters the agent context via dm.read_sdf(), dm.read_csv(), dm.read_excel(), and dm.open_df() (referenced in SKILL.md and references/io_module.md).
Boundary markers: None identified in the skill instructions.
Capability inventory: The skill allows for file writing (dm.to_sdf(), dm.to_xlsx()) and parallel processing via subprocesses (n_jobs).
Sanitization: While molecular structure sanitization (dm.sanitize_mol()) is present for chemical validity, there is no evidence of filtering for natural language instructions embedded in molecular data.

datamol