Back to plugin

Security audit

OpenViking

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this plugin suspicious because it found retrieved memory content being added to a high-trust prompt context, creating a prompt-injection risk; the review was static and did not test model behavior.

Consider whether you trust the memories and resources the plugin may retrieve, and whether you need automatic recall. Before installing, look for safeguards that keep retrieved text as reference data and require separate authorization for sensitive actions. The evidence is from static review; no exploit or model behavior was tested.

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
Findings (1)

MCP06

Warning
Location
dist/services/context-lifecycle-service.js:290
Finding

Untrusted recalled memory is inserted into system-prompt additions ## Remediation Suggestions 1. **Separate retrieved data from authoritative instructions.** Use a host-supported untrusted-content mechanism or a clearly identified data/tool-result channel instead of concatenating retrieved text into system-prompt additions. 2. **Enforce instruction precedence explicitly.** Trusted instructions should state that recalled memories, profiles, and resources are reference data: they cannot override system or developer instructions, authorize external actions, or establish user consent. 3. **Use structured serialization.** Preserve provenance separately from content and escape structural delimiters. Delimiter escaping is defense in depth, not a complete prompt-injection defense. 4. **Protect persistent sources.** Enforce authenticated write permissions, source ownership, and appropriate sharing boundaries for memories and profiles. Track provenance so suspicious content can be investigated and removed. 5. **Authorize sensitive actions independently.** Require host-enforced policy checks or explicit approval for credential access, filesystem uploads, destructive operations, and external communications. Retrieved instructions must never constitute authorization. 6. **Add adversarial regression tests.** Test instruction-bearing memories, forged closing tags, impersonated high-priority messages, and persistent poisoned profiles. Verify that sensitive actions remain blocked even when the model follows injected text.

Content
View full analysis

Vulnerability Details

File Location:

  • plugin/dist/services/context-lifecycle-service.js:290–293 — promotes retrieved content into a system-prompt addition.
  • plugin/dist/auto-recall.js:123–131 — wraps retrieved content without establishing an untrusted-data boundary.

Vulnerability Type: Indirect prompt injection / retrieved-content trust-boundary violation
Risk Level: Medium

Vulnerable Code

plugin/dist/auto-recall.js:123–131:

js
export function buildRecallContextBlock(memoryLines) {
    return [
        "<relevant-memories>",
        AUTO_RECALL_SOURCE_MARKER,
        "The following OpenViking memories may be relevant:",
        ...memoryLines,
        "</relevant-memories>",
    ].join("\n");
}

plugin/dist/services/context-lifecycle-service.js:290–293:

js
const systemPromptAddition = [assembled.systemPromptAddition, ...blocks].filter(Boolean).join("\n\n");
const estimatedTokens = assembled.estimatedTokens + estimateTextTokens(systemPromptAddition) - baseTokens;
if (estimatedTokens <= params.tokenBudget)
    return { ...assembled, systemPromptAddition, estimatedTokens };

Technical Analysis

The automatic recall flow obtains content from the configured OpenViking service through client.searchContext. It selects the returned content and passes it to buildRecallContextBlock, which interpolates that content verbatim.

The wrapper describes the material as relevant memories but does not explicitly prohibit treating embedded instructions as authoritative. It also preserves embedded delimiters and instruction-like text. During context assembly, the resulting recall block is concatenated into systemPromptAddition rather than kept in an explicitly untrusted data channel.

This creates an instruction/data trust-boundary violation: attacker-influenced retrieval content can reach a system-prompt addition. An attacker does not need to escape the wrapper to attempt instruction injection; preserving embedded closing tag ...[truncated 2187 chars]

SkillSpector findings are pending for this release.

Endor dependency reachability

Checked Nov 19, 2026 · 6:59 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.