T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:8- Finding
Excessive Tool Permissions for a Content-Generation Skill
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, line 8
Vulnerability Type: Excessive shell-execution and filesystem-read permissions
Risk Level: MediumVulnerable Code
yaml allowed-tools: Bash, ReadTechnical Analysis
The skill's documented purpose is to generate market-research advertising creative briefs. Its workflow consists of clarifying campaign requirements, producing and refining content, and optionally enriching supporting assets. None of these stated operations inherently requires arbitrary shell-command execution or unrestricted local-file access.
Granting both
BashandReadviolates the principle of least privilege:Bashmay allow the agent to execute local commands with the privileges of the hosting process.Readmay allow access to local files available to the hosting process.- Combining these capabilities increases the potential scope of prompt injection or compromised skill instructions because local data could be discovered, processed, and potentially exposed through available output channels.
The audited package does not contain executable scripts or direct instructions that actively abuse these tools. The risk arises from unnecessary capability exposure rather than confirmed malicious execution.
Attack Path
- A user installs and invokes the skill.
- The runtime grants the skill the declared
BashandReadcapabilities. - Attacker-controlled content enters the interaction, such as campaign material containing prompt-injection instructions, or the skill's instructions are later compromised.
- The injected instructions induce the agent to invoke
Readagainst accessible local files or execute commands throughBash. - Commands run and files are accessed with the permissions of the agent-hosting process.
- Retrieved information may be disclosed through the agent's response or another channel available to the runtime.
This path depends on the runtime honoring the declared permiss ...[truncated 801 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove both unnecessary permissions from the skill manifest:
yaml allowed-tools: []Alternatively, omit
allowed-toolsif the platform defaults to no tool access.-
If supporting assets must be read, replace unrestricted access with a narrowly scoped read capability limited to an explicit workspace directory and approved file types.
-
Do not grant
Bashunless a documented workflow strictly requires command execution. If it becomes necessary:- Allowlist exact commands and fixed arguments.
- Disable shell metacharacters, pipelines, redirection, and command substitution.
- Run commands in a sandbox with minimal filesystem and network access.
- Use a dedicated low-privilege account.
- Require user confirmation before every invocation.
-
Treat campaign briefs, uploaded documents, and other user-provided content as untrusted data. Explicitly prohibit following tool-use instructions embedded in that content.
-
Add automated manifest checks that reject tool permissions unsupported by the documented skill workflow.
