T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:27- Finding
Excessive Tool Permissions Violate Least Privilege
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This API-integration helper is mostly documentation and templates, but it declares broad read, write, and command-execution tools despite saying it does not execute API requests.
Review this skill before installing in an environment where tool declarations grant real access. It appears non-malicious and documentation-focused, but it should ideally remove exec and limit read/write to user-selected project files unless the publisher clearly defines when local execution is allowed.
SKILL.md:27Excessive Tool Permissions Violate Least Privilege
The description says to use the skill whenever API integration, interface docking, webhook configuration, or system connection is needed, and lists very broad audiences and scenarios. It does not define specific trigger phrases, boundaries, or negative examples beyond one excluded case, which could cause unintended invocation in many ordinary development contexts.
The description states '支持中文交互' and the feature note repeats Chinese interaction as a core capability, but the file does not offer a language choice or describe this as optional. This can violate language or locale policy if the skill defaults users into a specific language without opt-in.
The feature summary lists '中文交互' as a core capability in a way that suggests a default interaction mode, with no accompanying opt-in or alternative language behavior. Under the policy, language constraints should be optional or clearly justified.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# ...
def get_oauth_token(client_id, client_secret):
'https://api.example.com/oauth/token',
data={
'grant_type': 'client_credentials',
'client_id': client_id,
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import requests
# ...
def get_oauth_token(client_id, client_secret):
'https://api.example.com/oauth/token',
data={
'grant_type': 'client_credentials',
'client_id': client_id,
The skill presents conflicting operational boundaries: it claims it does not execute actual API requests, yet elsewhere classifies itself as MD+EXEC and discusses command execution and execution-related failure modes. This ambiguity can cause an agent or user to over-grant permissions or invoke execution paths unexpectedly, increasing the risk of network actions or shell use beyond the stated scope.