Back to skill

Security audit

Social Calendar Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed social media calendar planning helper with scoped memory use and explicit user confirmation before saving results.

Install only if you want this skill to read relevant project social-channel memory and, with confirmation, save calendar outputs or propose cadence updates. It should not post, schedule, or ship content by itself.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md
## Save Results

After delivering the calendar, ask: "Save these results for future sessions?" On confirmation, save to `memory/social/social-calendar-builder/YYYY-MM-DD-<topic>.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Cadence commitments and channel facts go only to `memory/events/channels.ndjson` via an authorized `operation: propose` request to `registry-events.py` — [channel-registry](../../../protocol/channel-registry/SKILL.md) is the sole writer of `memory/channels/`. Do not write memory without asking.

## Reference Materials

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file includes a bilingual display name and Chinese-only summary text, then repeats Chinese trigger text in the description. This introduces a language expectation in the skill surface without stating that language output is optional or user-selected, which can conflict with a policy requiring language/locale choice unless the constraint is justified.

Content

No source excerpt is available for this finding.