pi-media-transcribe@0.2.4
Local-first transcription to structured Markdown notes: transcribe YouTube, podcasts and meetings offline with Whisper or Qwen3-ASR, then optionally have an LLM proofread, segment, summarize and file into any notes folder or Obsidian vault.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe helper can automatically send saved OpenAI or OpenRouter credentials to the unrelated default DeepSeek endpoint when no explicit key or endpoint is set. This is credential exfiltration in the user-invoked polished workflow.
Static reason
No blocking static signals were detected.
Trigger
A user runs the polished transcription-to-note workflow with no explicit API key or endpoint configured and has an OpenAI or OpenRouter key saved in Pi auth.json.
Impact
A credential for OpenAI or OpenRouter may be disclosed to an unrelated service; the transcript is also sent to that endpoint for processing.
Mechanism
The helper selects a key from Pi's saved DeepSeek, OpenAI, or OpenRouter credentials, discards its provider identity, defaults the endpoint to api.deepseek.com, and sends the key in the Bearer authorization header.
Attack narrative
When the polished note workflow runs without an explicit key or endpoint, the helper may fall back to Pi's saved credentials. It accepts the first key from DeepSeek, OpenAI, or OpenRouter but does not preserve the provider identity. The default endpoint is DeepSeek, and the selected key is sent as a Bearer token there. Thus a saved OpenAI or OpenRouter credential can be disclosed to DeepSeek along with the transcript.
AI rationale
The helper can automatically send saved OpenAI or OpenRouter credentials to the unrelated default DeepSeek endpoint when no explicit key or endpoint is set. This is credential exfiltration in the user-invoked polished workflow.
Evidence
skills/media-transcribe/scripts/llm_to_obsidian.pyskills/media-transcribe/scripts/to-obsidian.shskills/media-transcribe/SKILL.md~/.pi/agent/auth.jsonthe configured notes vault destination
Network endpoints1
api.deepseek.com/v1/chat/completions
Decision evidence
public snapshotAI called this Malicious at 98.0% confidence as Malware with low false-positive risk.
Evidence for block
- The LLM fallback reads saved credentials for DeepSeek, OpenAI, or OpenRouter from ~/.pi/agent/auth.json and returns the first available key without retaining which provider it came from.
- When no endpoint is configured, the helper defaults to https://api.deepseek.com, regardless of which provider supplied the saved key.
- The helper sends the selected key as a Bearer token to the configured endpoint's /v1/chat/completions API.
- The default polished-note path passes the transcript to this helper; the skill directs users to use polished mode for readable notes or summaries.
Evidence against
- The LLM request runs as part of the user-invoked polished transcription workflow, and the package describes the LLM step.
- Users can set LLM_BASE_URL or a configured baseUrl to select an endpoint; --raw skips the LLM call.
Behavioral surface
Source & flagged code
6 flaggedskills/media-transcribe/scripts/llm_to_obsidian.pyView file
251for provider in ("deepseek", "openai", "openrouter"):
key = (data.get(provider) or {}).get("key")
if isinstance(key, str) and key.strip():
return key.strip()
return
High
Ai Review Evidence
The LLM fallback reads saved credentials for DeepSeek, OpenAI, or OpenRouter from ~/.pi/agent/auth.json and returns the first available key without retaining which provider it came from.
skills/media-transcribe/scripts/llm_to_obsidian.pyView on unpkg · L251233base_url = (os.environ.get("LLM_BASE_URL") or llm.get("baseUrl") or "https://api.deepseek.com").rstrip("/")
model = os.environ.get("LLM_MODEL") or llm.get("model") or "deepseek-chat"
if not api_ke
High
Ai Review Evidence
When no endpoint is configured, the helper defaults to https://api.deepseek.com, regardless of which provider supplied the saved key.
skills/media-transcribe/scripts/llm_to_obsidian.pyView on unpkg · L233313f"{base_url}/v1/chat/completions",
data=json.dumps(payload).encode("utf-8"),
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
)
t
Findings
5 High1 Medium
HighAi Review Evidenceskills/media-transcribe/scripts/llm_to_obsidian.py
HighAi Review Evidenceskills/media-transcribe/scripts/llm_to_obsidian.py
HighAi Review Evidenceskills/media-transcribe/scripts/llm_to_obsidian.py
HighAi Review Evidenceskills/media-transcribe/SKILL.md
HighAi Review Evidenceskills/media-transcribe/scripts/to-obsidian.sh
MediumShips Build Helperskills/media-transcribe/scripts/llm_to_obsidian.py
Affected versions and remediation
This report applies to pi-media-transcribe@0.2.4.
See all versions of pi-media-transcribe for other recorded verdicts.
- Avoid installing pi-media-transcribe@0.2.4. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.