research-lookup
5 findings (3 critical, 2 medium), mainly data exfiltration. Most recent scan 2026-10-21.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Compiles current scholarly evidence for a scientific manuscript or research brief when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source retrieval, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.
- Package
- 5 files, 102 KB
- SKILL.md
- 2105 words, 12+ sections
- Code
- Python (2)
- License
- MIT license
- Compatibility
- Requires Python 3.10+ and network access; targets parallel-web-tools CLI 0.9.3 for Search, Extract, and Research. Explicit Chat requires requests and PARALLEL_API_KEY; optional Perplexity through openrouter.ai requires requests and OPENROUTER_API_KEY.
SKILL.md covers: Research Lookup · Scope and boundaries · Parallel-first routing · Recommended manuscript workflow · 1. Capture manuscript context · 2. Run the academic evidence pipeline · 3. Verify promising sources with Parallel Extract · 4. Review the manuscript research packet · 5. Use evidence in the manuscript safely · Reference quality rules · Explicit deep research · Explicit Parallel Chat
Findings
CRITICAL Cross-file env var exfiltration: 1 files Data Exfiltrationbehavioral
Environment variable access with network calls in scripts/research_lookup.py
CRITICAL Cross-file exfiltration chain: 2 files Data Exfiltrationbehavioral
Multi-file exfiltration chain detected: scripts/research_lookup.py collect data → scripts/manuscript_packet.py → scripts/research_lookup.py transmit to network
CRITICAL Environment variable access with network calls detected Data Exfiltrationbehavioral
Script accesses environment variables and makes network calls in /home/runner/work/skill-scanner-test/skill-scanner-test/skills/K-Dense-AI-scientific-agent-skills/skills/research-lookup/scripts/research_lookup.py
/home/runner/work/skill-scanner-test/skill-scanner-test/skills/K-Dense-AI-scientific-agent-skills/skills/research-lookup/scripts/research_lookup.py
MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: requests.post(
scripts/research_lookup.py:766
response = requests.post(MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: requests.post(
scripts/research_lookup.py:837
response = requests.post(What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 4.1 KB |
SKILL.md | doc | 17 KB |
references/api-contracts.md | doc | 6.5 KB |
scripts/manuscript_packet.py | script | 27 KB |
scripts/research_lookup.py | script | 47 KB |
External hosts referenced
docs.parallel.ai openrouter.ai api.parallel.ai doi.org arxiv.org github.com export.arxiv.org parallel.ai pypi.org
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
PARALLEL_API_KEY OPENROUTER_API_KEY
Package contents recorded 2026-10-22 at commit 593377bb0487. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/K-Dense-AI/scientific-agent-skills
- Raw scan result: skills-research-lookup-scan.json
- Badge for your README:
- Request a re-scan