Back to skill

Security audit

Session Context Bridge

Security checks for vulnerabilities and agentic risk

Overview

This skill locally saves and restores project session notes in markdown files; the behavior is disclosed and purpose-aligned, but users should avoid storing secrets in those notes.

Install only if you want local cross-session project notes. Keep the .context directory out of source control when it may contain sensitive project state, review entries before saving or restoring them, and never place secrets, tokens, passwords, connection strings, customer data, or raw credential files in these markdown files.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

Environment

  • Node v22.22.2, pnpm 10.28
  • DATABASE_URL in .env (not committed)
  • Redis running on localhost:6379
text

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README promotes automatic persistence of session context into markdown files but does not warn users that data will be retained across sessions and written to disk. Because context may contain sensitive project details, credentials, or internal reasoning, lack of disclosure can lead to unintentional retention, later disclosure, or corruption of user data. In this skill's context, persistence is the core feature, so missing safety guidance makes the risk more significant rather than less.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README instructs users to invoke generic phrases like 'save my context', 'restore my context', and 'update context'. Broad trigger phrases can overlap with ordinary conversation, increasing the chance the agent performs persistent read/write operations when the user did not intend to activate the skill. In a skill that carries context across sessions, accidental activation can expose prior session data or overwrite stored state.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly tells users to preserve 'environment details' and later demonstrates storing credential-related state in markdown context files. Persisting secrets or secret-adjacent configuration in .context/current.md and archives increases the chance of accidental disclosure through source control, backups, screen sharing, or later agent access across sessions.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages carrying forward broad project state, including unfinished tasks, file relationships, environment details, and credential setup, across sessions in plain-language summaries. This expands the persistence and visibility of sensitive operational context, making data leakage more likely and increasing the blast radius if the context directory is exposed or ingested by other tools.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The example session context includes credential-related information in the Environment section without any warning or masking guidance. Even mentioning secret-bearing variables and setup details in durable markdown artifacts normalizes unsafe secret handling and can help attackers identify high-value files or services to target.

Content

No source excerpt is available for this finding.