T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:11- Finding
Unnecessary Command Execution and Filesystem Write Permissions
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:11-15
Vulnerability Type: Excessive agent tool permissions
Risk Level: Mediumyaml tools: - Read - Write - Bash - ExecTechnical Analysis
The Skill requests filesystem write access and two command-execution tools, although its implementation only performs in-memory keyword matching, recommendation, workflow analysis, scoring, and guide generation. No implemented function in
src/index.jsrequiresWrite,Bash, orExec.This violates the principle of least privilege. If tool availability is derived from this manifest, an injected instruction, malicious task, or future compromise of the Skill context could invoke these capabilities even though they are unrelated to the declared discovery and recommendation functionality.
The audit did not identify instructions or implementation code that currently abuses these permissions. The risk results from unnecessarily exposing powerful tools that could be abused if the agent's decision-making context is manipulated.
Attack Path
- The platform loads the Skill and grants the tools declared in
SKILL.md. - The Skill consequently receives
Write,Bash, andExeccapabilities despite not needing them for its implemented behavior. - An attacker supplies a malicious task or introduces injected content into data processed by the agent.
- The manipulated agent invokes
BashorExecto run attacker-selected commands, or usesWriteto alter files. - Commands execute and files are modified within the permissions and sandbox boundaries of the hosting agent process.
Impact Assessment
Successful exploitation could provide arbitrary command execution with the operating-system privileges assigned to the agent runtime. It could also permit creation, modification, or deletion of files accessible through the
Writetool. The precise scope depends on platform sandboxing, tool confir ...[truncated 285 chars]- The platform loads the Skill and grants the tools declared in
- Remediation
View remediation
Remediation Suggestions
- Remove
Write,Bash, andExecfrom the declared tool list. - Remove
Readas well if the Skill continues to receive its skill catalog as an in-memory argument. If catalog loading later requires file access, restrict reading to a dedicated catalog directory. - Declare only the minimum tools required by implemented functionality.
- Enforce platform-level command allowlists, filesystem path restrictions, sandboxing, and explicit user approval for any future command-execution capability.
- Add a security test that compares declared tools against capabilities actually used by the implementation.
- Require a separate security review before introducing filesystem mutation or process-execution functionality.
- Remove
