Scan Report
15 /100
meeting-minutes-retriever
Read meeting minutes or notes from a local file path or URL, or inspect a local meeting-notes directory and report the file count plus file list.
A legitimate meeting minutes retriever skill that uses declared subprocess calls for directory listing and local file/URL reading with no malicious behavior detected.
Safe to install
Approve for use. Consider pinning the requests library version for supply chain hygiene.
Findings 2 items
| Severity | Finding | Location |
|---|---|---|
| Low | Unpinned requests dependency Supply Chain | scripts/read_meeting_data.py:7 |
| Low | SKILL.md frontmatter lacks explicit allowed-tools declaration Doc Mismatch | SKILL.md:1 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | READ | READ | ✓ Aligned | SKILL.md declares local file reading; read_meeting_data.py implements os.path.ab… |
| Network | READ | READ | ✓ Aligned | SKILL.md declares URL fetching; read_meeting_data.py implements requests.get() |
| Shell | WRITE | WRITE | ✓ Aligned | SKILL.md declares OS-appropriate system commands; list_meeting_files.py uses sub… |
| Environment | NONE | NONE | — | No os.environ access observed |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser automation |
| Database | NONE | NONE | — | No database access |
| Skill Invoke | NONE | NONE | — | No cross-skill invocation |
File Tree
6 files · 10.9 KB · 271 lines Python 2f · 186L
Markdown 1f · 79L
YAML 1f · 4L
Text 2f · 2L
├─
▾
agents
│ └─
openai.yaml
YAML
├─
▾
scripts
│ ├─
list_meeting_files.py
Python
│ └─
read_meeting_data.py
Python
├─
sample_meeting_gbk.txt
Text
├─
sample_meeting.txt
Text
└─
SKILL.md
Markdown
Dependencies 1 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
requests | * | pip | No | Version not pinned; import in scripts/read_meeting_data.py |
Security Positives
✓ Subprocess calls are limited to OS-native file listing commands (find/PowerShell) with no arbitrary command execution
✓ File and URL reading returns data only to the caller, with no exfiltration
✓ No credential harvesting or sensitive path access detected
✓ No obfuscation, base64 encoding, or hidden instructions
✓ Multi-encoding fallback for local file reading is a good robustness practice
✓ Error messages are user-friendly and do not leak system internals
✓ Documentation accurately describes the tool's actual behavior with no mismatches
✓ Subprocess usage is declared in SKILL.md under the Tool Contract section