T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:16- Finding
Excessive File-Read and Command-Execution Permissions
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a review concern because it presents itself as an interview helper while requesting broad read and command-execution tools and documenting vague automation, API, file, and command workflows.
Review this before installing. The artifact does not show exfiltration, destructive code, or persistence, but it asks for powerful read and command-execution capability while its purpose and operating boundaries are unclear. Install only if you are comfortable granting those tools to this skill, or require the publisher to remove exec/read or document exact scoped operations and consent requirements.
SKILL.md:16Excessive File-Read and Command-Execution Permissions
The manifest presents this as a narrow intent-elicitation interview skill, but the body describes broad automation, data processing, workflow orchestration, and GitHub/API-backed operations. This mismatch can mislead users and policy engines into granting trust or capabilities under false pretenses, increasing the risk of unexpected data access or execution paths.
Declaring the 'exec' capability for a skill whose stated purpose is only to ask one clarifying question at a time violates least privilege. If the platform enables this tool, the skill could execute local commands unnecessarily, creating avoidable risk of command execution, file access, or chained abuse through prompt steering.
The documentation expands the skill into API credential setup, file handling, network/API calls, and command execution despite no legitimate need for those actions in an intent-interview workflow. This broadens the operational surface and normalizes sensitive behaviors that could expose credentials, touch local files, or run commands under the guise of a harmless clarification tool.
The trigger condition 'when the user needs to perform related operations' is so broad that the skill could activate in many unrelated contexts. Overbroad activation increases the chance that a privileged or misleadingly documented skill is invoked without clear user intent, enabling unnecessary access or execution opportunities.
The file claims a one-question-at-a-time intent extraction behavior, but most of the content documents generic automation and processing features instead. This inconsistency increases the likelihood of deceptive or confusing deployment, where reviewers and users underestimate what the skill is designed to do.
The skill references API keys, access credentials, and command execution but does not clearly warn users that it may touch sensitive secrets or perform executable actions. In the context of a supposedly benign interview skill, this omission is especially dangerous because users are less likely to expect or scrutinize privileged behavior.