Ae1
High
- Category
- analysis-evasion
- Content
- Source code is bundled inside this skill at `scripts/time.mjs`.
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
Time
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed local time-planning helper that writes a small timeline file and does not show hidden network, credential, persistence, or privilege behavior.
Install only if you are comfortable with a local CLI creating and updating time.md in the current directory. Avoid init --force or rm -f time.md unless you are in a scratch directory or have confirmed there is no important existing time.md file.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The instruction requires use of one specific metaphor and marks an alternative phrasing as incorrect, effectively forcing a language style choice. This is a natural-language policy concern because it imposes a linguistic constraint without offering user choice or documenting a justified locale/policy need.
Missing User Warnings
Medium
- Confidence
- 90% confidence
- Finding
- The `init [--force]` command is documented as overwriting an existing `time.md` file, but the skill does not prominently warn about data loss or recommend checking the working directory before use. In agent-driven workflows, this can lead to unintended destruction of user files if run in the wrong directory or with stale path assumptions.
Missing User Warnings
Medium
- Confidence
- 92% confidence
- Finding
- The scratch-pad example ends with `rm -f time.md` without an explicit warning, normalization of path safety, or emphasis that deletion occurs in the current directory. Although the example uses `/tmp`, agents or users may adapt or partially copy the pattern into other directories, causing accidental file deletion.
Static analysis
No suspicious patterns detected.