中文 EN

Scan Report

Scan New Files

✓ Trusted — Risk Score 5/100
Last scan:2 days ago Rescan
5 /100
oasis-audio
AI audio narration generator that reads local conversation history and sends composed anonymized text prompts to xplai.ai for audio generation
Oasis Audio is a well-designed audio generation skill with strong data-safety controls, explicit content sanitization, and no evidence of credential harvesting, remote code execution, or data exfiltration beyond its declared API endpoint.
Skill Nameoasis-audio
Duration36.9s
Enginepi
✓
Safe to install
Approve for use. No security concerns require mitigation.

Findings 2 items

Severity Finding Location
Low
Audit log write not declared in SKILL.md
xplai_gen_audio.py writes an audit.log file locally. SKILL.md declares filesystem:READ only. The write is benign (local, on-demand, debug-optional), but not documented.
with open(AUDIT_LOG_PATH, 'a', encoding='utf-8') as f:
→ Add 'filesystem:WRITE' for audit.log or gate writes behind a flag to avoid local filesystem side effects.
 xplai_gen_audio.py:44
Low
Network scope wording mismatch
SKILL.md describes network access as HTTPS requests (read-like framing) but the actual operation is POST/GET which sends data. Declared 'READ' but operates as 'WRITE' for the audio generation step.
Network: HTTPS requests to xplai.ai only
→ Clarify that the skill sends composed text prompts to xplai.ai (network:WRITE) rather than reading from it.
 SKILL.md:158
ResourceDeclaredInferredStatusEvidence
Filesystem READ READ+WRITE ✓ Aligned xplai_gen_audio.py:44 - AUDIT_LOG_PATH write; debug_utils.py debug logging
Network READ WRITE ✓ Aligned xplai_gen_audio.py:75 - POST requests send text payload to xplai.ai; SKILL.md co…
Shell NONE NONE — No subprocess, os.system, or shell execution found
Environment NONE NONE — No os.environ iteration or credential access
Skill Invoke NONE NONE — No nested skill invocation
Clipboard NONE NONE — No clipboard access
Browser NONE NONE — No browser automation
Database NONE NONE — No database access
3 findings
🔗
Medium External URL 外部 URL
https://eagle-api.xplai.ai
SKILL.md:3
🔗
Medium External URL 外部 URL
https://www.xplai.ai/
SKILL.md:26
🔗
Medium External URL 外部 URL
https://www.xplai.ai/#/video/
xplai_status.py:55

File Tree

7 files · 47.4 KB · 1063 lines
Python 4f · 683L Markdown 3f · 380L
├─ 📝 audio_modes.md Markdown 45L · 3.0 KB
├─ 🐍 context_collector.py Python 393L · 12.9 KB
├─ 🐍 debug_utils.py Python 52L · 1.4 KB
├─ 📝 SKILL.md Markdown 200L · 11.5 KB
├─ 📝 text_architecture.md Markdown 135L · 10.3 KB
├─ 🐍 xplai_gen_audio.py Python 154L · 5.4 KB
└─ 🐍 xplai_status.py Python 84L · 2.9 KB

Dependencies 1 items

PackageVersionSourceKnown VulnsNotes
Python stdlib only N/A stdlib No Uses only http.client, json, re, pathlib, datetime, argparse — no third-party packages

Security Positives

✓ Active content sanitization: SENSITIVE_PATTERNS regexes block API keys, passwords, SSH keys, Bearer tokens, emails, and file paths from being sent to the API
✓ Strict data scoping: Only composed text prompts (anonymized ~1000 chars) are transmitted; raw conversation history, session files, and USER.md are never sent externally
✓ No credential access: No API key storage, no environment variable enumeration, no ~/.ssh or ~/.aws path access
✓ No shell execution: No subprocess, os.system, eval, base64 piping, or curl|bash patterns found anywhere
✓ Sensitive scene classification: Health, financial, legal, and relationship topics extract emotional tone only — specifics are never quoted
✓ Local-only context collection: context_collector.py operates entirely on-device with read-only session access
✓ No third-party telemetry or analytics
✓ No hardcoded secrets or embedded tokens in any file
✓ Version-agnostic stdlib-only dependencies (http.client, json, re, pathlib)