Hugging Face Hub MCP
https://huggingface.co/mcp
github.com/huggingface/hf-mcp-server
Severity breakdown
Worst finding
Tool `hub_repo_details` accepts an unbounded monetary / quota value
· hub_repo_details
The numeric parameter(s) `limit` have a money/quota-shaped name but no `maximum` constraint. An LLM tricked by indirect-injection can call the tool with arbitrarily large values.
fix: Add a `maximum` (and ideally `minimum`) to each money/quota numeric, OR enforce the cap via a capframe-bind `--limit` caveat at the agent boundary.
All 3 findings
- highTool `hub_repo_details` accepts an unbounded monetary / quota value· hub_repo_detailsexcessive agency
The numeric parameter(s) `limit` have a money/quota-shaped name but no `maximum` constraint. An LLM tricked by indirect-injection can call the tool with arbitrarily large values.
fix: Add a `maximum` (and ideally `minimum`) to each money/quota numeric, OR enforce the cap via a capframe-bind `--limit` caveat at the agent boundary.
- mediumTool `hub_repo_search` accepts unconstrained string input· hub_repo_searchunconstrained input
The following string parameter(s) have no `maxLength` constraint: `author`, `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `hub_repo_details` accepts unconstrained string input· hub_repo_detailsunconstrained input
The following string parameter(s) have no `maxLength` constraint: `config`, `split`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
How this was scored
Source http — live HTTP MCP endpoint, classified against every rule. Findings are emitted by the public capframe.findings.v1 schema. Score = 100 − (10·Critical + 4·High + 2·Medium + 1·Low), clamped to [0, 100].
Disagree with a finding? Open an issue.