critical
suspicious.generated_source_template_injection
- Location
- SKILL.md:67
- Finding
- User-controlled placeholder is embedded directly into generated source code.
ZeeLin Deep Research 深度研究
AdvisoryAudited by Static analysis on May 10, 2026.
Overview
Detected: suspicious.generated_source_template_injection
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
NoteHigh Confidence
ASI02: Tool Misuse and ExploitationWhat this means
When used, the agent may run the included shell script to contact the ZeeLin service.
Why it was flagged
The skill tells the agent to run a local script via exec. This is disclosed and central to the API workflow, but users should notice that using the skill involves command execution.
Skill content
优先用 `exec` 调用脚本 `scripts/research.sh` 一次性完成
Recommendation
Use the skill only if you are comfortable with the documented script execution and external API workflow.
NoteHigh Confidence
ASI03: Identity and Privilege AbuseWhat this means
You must provide a ZeeLin API key, and that key will be used to authenticate requests to the provider.
Why it was flagged
The script requires a ZeeLin API key from the environment. This is expected for the service integration, but the registry metadata lists no required env vars or primary credential.
Skill content
API_KEY="${DESEARCH_API_KEY:-}"Recommendation
Use a dedicated, revocable API key and be aware that the registry metadata under-declares this credential requirement.
NoteHigh Confidence
ASI07: Insecure Inter-Agent CommunicationWhat this means
Research questions, which may contain business or personal information, are uploaded to desearch.zeelin.cn for processing.
Why it was flagged
The script sends the user's research content and API authentication to the external ZeeLin API. This is disclosed and purpose-aligned, but the artifacts do not describe provider retention or privacy boundaries.
Skill content
RESP=$(curl -s -X POST "${BASE_URL}/api/conversation/anew" ... -H "x-api-key: ${API_KEY}" ... -d "$BODY")Recommendation
Avoid submitting sensitive or confidential information unless you trust ZeeLin’s service terms and data handling.