reactome-database
Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
High
Do not use without reviewing
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill shows CLI commands that require passing analysis "tokens" via a --token argument (placeholders like TOKEN), which would force an agent to embed secret token values verbatim into generated commands/outputs to retrieve or download results, creating an exfiltration risk.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
High: the runtime path performs GET/POST to Reactome endpoints and reads outsider-fetched JSON/text (`scripts/reactome_analysis.py` → `_CLIENT.fetch_text` / `fetch_bytes`, then `json.loads(result)` and `_write_output`), which can include arbitrary text fields that could be repackaged into the agent’s subsequent LLM context.
- Repository
google-deepmind/science-skills
- Revision
4de6786
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.