Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
公众号选题雷达
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed WeChat topic-research tool that uses a user-provided API key to fetch public article data and generate local reports.
Install only if you intend to research WeChat public-account topics using the Mangg Cloud API. Keep the API key out of shared files and logs, review the cost estimates before running larger scans, and choose output paths you are comfortable writing reports or snapshots to.
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (17)
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
python scripts/topic_radar.py \
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill describes capabilities that require network access, reading secrets from environment variables, and writing files, but it declares no explicit tool scope or permission boundaries. In an agent environment, this can enable over-privileged execution, increasing the chance of unintended external requests, secret exposure, or uncontrolled file output if the skill is triggered in the wrong context.
Vague Triggers
Medium
- Confidence
- 94% confidence
- Finding
- The description and trigger conditions are broad enough to match many ordinary content-planning requests, which can cause the skill to activate unexpectedly. Because the skill performs network collection, uses an API key, and may incur cost, over-broad triggering creates a real risk of unintended data access or billable actions without sufficiently specific user intent.
Vague Triggers
Medium
- Confidence
- 90% confidence
- Finding
- The invocation guidance explicitly says plain-language requests like 'help me find topics' or 'what can I write' should match, without strong boundaries. In context, this is more dangerous because the skill can perform network lookups, consume a paid API, and produce files, so ambiguous matching can escalate a casual brainstorming request into external actions.
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The module-level description and all user-facing strings are written in Chinese, and the generated HTML explicitly sets `lang="zh-CN"`, indicating the skill is designed to operate only in Chinese. The file does not offer any language or locale choice, nor document this as a justified region-specific constraint, so it conflicts with the language/locale choice policy.
Static analysis
No suspicious patterns detected.