Back to skill

Security audit

Softr

Security checks for vulnerabilities and agentic risk

Overview

The Softr operations have clear approval controls, but the required CLI can also install additional agent skills without this skill explaining that broader effect.

Review and install the CLI separately before use, and decide whether its additional agent skills are wanted. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill writes; configure it before invoking oo if those changes are unwanted. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Limit connected Softr permissions and retain write/delete approvals. The remote installer and hosted connector implementation were not verified.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared purpose concerns Softr data operations, whereas the supplied command executes an Oomol-hosted installer. Nothing in the provided chunk establishes that this installation supports Softr, so it cannot be treated as a demonstrated supporting implementation detail. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
- `get_record` — Get one Softr table record by ID.
- `get_table` — Get one Softr table and its field definitions by database ID and table ID.
- `get_table_field` — Get one Softr table field definition by ID.
- `list_databases` — List the Softr databases accessible to the connected Personal Access Token.
- `list_records` — List a paginated page of records from one Softr table, optionally filtered by a table view.
- `list_table_views` — List the configured views for one Softr table.
- `list_tables` — List all tables in a Softr database, including their field definitions.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback installation command pipes a remotely fetched, unpinned script directly into Bash without integrity verification or review; the PowerShell alternative follows the same fetch-and-execute pattern. If the distribution endpoint or release pipeline is compromised, installation could execute attacker-controlled code with the invoking user's privileges, although the missing-CLI prerequisite limits when this path is reached.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources