T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:9- Finding
Excessive Tool Permissions Violate Least-Privilege Requirements
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 9–12
Vulnerability Type: Excessive filesystem, persistent-memory, external invocation, event publication, and inter-agent communication permissions
Risk Level: MediumVulnerable Configuration
markdown | `business-researcher` | Business research agent. Scouts profitable software opportunities across app stores, Amazon KDP, freelance platforms, GitHub, news, and social media. | web_search, web_fetch, file_read, file_write, file_list, memory_store | | `researcher` | Research agent. Fetches web content and synthesizes information. | web_search, web_fetch, file_read, file_write, file_list, memory_store | | `risk-officer` | Continuous risk monitor for trading rails, drawdown, kill switch, and flatten events. | memory_store, memory_recall, event_publish, mcp.invoke | | `reviewer` | Pipeline reviewer. Reviews proposed changes for correctness, maintainability, tests, and release readiness. | file_read, file_list, memory_store, memory_recall, agent_send |Technical Analysis
The declared purpose of the Skill is to assemble a due-diligence dossier from public sources. Web search, web retrieval, and narrowly scoped output writing are reasonably related to that purpose. However, the roles also receive broad capabilities that are not shown to be necessary for the documented workflow:
- Research roles can read, enumerate, and write local files without a documented workspace restriction.
- Multiple roles can write information to persistent memory.
- The risk officer can retrieve persistent data, publish events, and invoke unspecified MCP capabilities.
- The reviewer can retrieve persistent memory and transmit information to another agent.
- The risk officer's trading-oriented responsibilities, including kill-switch and flatten events, are unrelated to the stated public-source dossier workflow.
No allowlists, path restrictions, destination controls, MCP m ...[truncated 2445 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove
file_read,file_list, andfile_writefrom roles that do not require local-file access. - If dossier files must be processed, restrict all filesystem operations to a dedicated per-task workspace and block traversal, absolute paths, symlinks escaping the workspace, and access to credentials or configuration directories.
- Remove
memory_storeandmemory_recallunless cross-session retention is an explicit requirement. If retained, use task-scoped namespaces, expiration periods, provenance labels, and sensitive-data filtering. - Remove the trading-oriented risk-officer role and its kill-switch or flatten-event responsibilities unless they are separately justified by the Skill's declared purpose.
- Replace unrestricted
mcp.invokewith an allowlist of named MCP servers, methods, parameters, and destinations. Require human approval for operations with external side effects. - Restrict
event_publishandagent_sendto predefined recipients and schemas. Prevent messages from containing local-file contents, credentials, secrets, or unreviewed persistent-memory records. - Treat all fetched web content as untrusted data rather than executable instructions. Add explicit controls preventing web content from changing role objectives or authorizing tool calls.
- Apply egress controls so
web_fetchcan access only required HTTP or HTTPS destinations and cannot reach loopback, link-local, private-network, metadata-service, or file URLs. - Add audit logging for file access, memory operations, MCP calls, event publication, and inter-agent messages, including origin, destination, and user approval state.
- Expand the evaluation set with tests for prompt injection, workspace escape, sensitive-file access, persistent-memory poisoning, unauthorized MCP invocation, and attempted data exfiltration.
- Remove
