Scan Report
5 /100
adverse-event-narrative
Generate CIOMS-compliant adverse event narratives for Individual Case Safety Reports (ICSR)
Legitimate pharmacovigilance tool that generates CIOMS-compliant adverse event narratives from JSON case data with no malicious behavior detected.
Safe to install
No action required. The skill is safe to use as a text generation tool for regulatory pharmacovigilance workflows.
Findings 1 items
| Severity | Finding | Location |
|---|---|---|
| Low | Over-declared allowed-tools Doc Mismatch | SKILL.md:7 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | WRITE | WRITE | ✓ Aligned | scripts/main.py:240-244 writes output file |
| Filesystem | READ | READ | ✓ Aligned | scripts/main.py:221-227 reads input JSON |
| Network | NONE | NONE | — | No network imports or requests in scripts/main.py |
| Shell | WRITE | NONE | ✓ Aligned | scripts/main.py uses only Python standard library; no subprocess, os.system, or … |
| Environment | NONE | NONE | — | No os.environ access or environment variable reading |
| Skill Invoke | NONE | NONE | — | No skill invocation capabilities present |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser/web automation |
| Database | NONE | NONE | — | No database connectivity |
File Tree
8 files · 38.0 KB · 1270 lines Markdown 5f · 783L
Python 1f · 372L
JSON 2f · 115L
├─
▾
references
│ ├─
CIOMS_I_Guidelines.md
Markdown
│ ├─
ICSR_Template.md
Markdown
│ ├─
MedDRA_Reference.md
Markdown
│ ├─
Quick_Reference.md
Markdown
│ ├─
sample_case_001.json
JSON
│ └─
sample_case_minimal.json
JSON
├─
▾
scripts
│ └─
main.py
Python
└─
SKILL.md
Markdown
Security Positives
✓ No network requests or external communication detected
✓ No credential harvesting or environment variable access
✓ No obfuscation techniques (no base64, eval, or atob)
✓ No sensitive file path access (~/.ssh, ~/.aws, .env)
✓ No remote script execution (no curl|bash or wget|sh patterns)
✓ No subprocess or shell command execution in code
✓ Uses only Python standard library with zero external dependencies
✓ Clean, readable code with proper error handling
✓ Legitimate pharmacovigilance use case with regulatory compliance focus
✓ No data exfiltration or C2 communication patterns