ClawHub
Back to skill

Security audit

Calendar Reminders (gcalcli + CalDAV)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed calendar reminder planner that reads configured calendars and outputs reminder plans, with expected but sensitive calendar/OAuth integration risks.

Install only if you are comfortable giving gcalcli/khal access to calendar data and OAuth sessions. Use trusted, preferably absolute paths for configured binaries, review any cron job before enabling it, and expect reminder JSON to contain calendar titles, IDs, labels, and reminder times.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
- `scripts/calendar_reminder_plan.py` — produces a JSON plan for reminder scheduling

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
- `scripts/calendar_reminder_plan.py` — produces a JSON plan for reminder scheduling

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
## Auth (Google)

`gcalcli` requires OAuth. On headless servers you may need SSH port-forwarding.
The wrapper uses `--noauth_local_server` to print instructions.

## Reminder planning

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · scripts/calendar_reminder_plan.py (reported line 66)May include surrounding context.

python
start_local = dt.datetime(day_local.year, day_local.month, day_local.day, 0, 0, tzinfo=tz_local)
    end_local = start_local + dt.timedelta(days=1)

    env = dict(os.environ)
    env.setdefault("PYTHONWARNINGS", "ignore::FutureWarning")
    env["TZ"] = "UTC"

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · scripts/calendar_reminder_plan.py (reported line 107)May include surrounding context.

python
start_local = dt.datetime(day_local.year, day_local.month, day_local.day, 0, 0, tzinfo=tz_local)
    end_local = start_local + dt.timedelta(days=1)

    env = dict(os.environ)
    env.setdefault("PYTHONWARNINGS", "ignore::FutureWarning")
    env["TZ"] = "UTC"

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/calendar_reminder_plan.py (reported line 90)May include surrounding context.

python
end_local.isoformat(timespec="minutes"),
    ]

    out = subprocess.check_output(cmd, text=True, env=env)
    return list(csv.DictReader(out.splitlines(), delimiter="\t"))

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/calendar_reminder_plan.py (reported line 118)May include surrounding context.

python
end_local.isoformat(timespec="minutes"),
    ]

    out = subprocess.check_output(cmd, text=True, env=env)
    return list(csv.DictReader(out.splitlines(), delimiter="\t"))

Static analysis

No suspicious patterns detected.