T07 · Tool Hijacking and Spoofing
- Location
references/throughput-dashboard.js:29- Finding
Arbitrary Code Execution Through Dynamic Loading of a Workspace Metrics Module
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This observability skill has a legitimate purpose, but it needs review because it installs recurring monitoring that stores agent outputs and dynamically loads workspace code.
Install only if you want persistent observability files in this workspace. Review who can write to scripts/session-metrics.js and INTENT.md before enabling cron, and treat memory/decisions-audit.jsonl and memory/traces as potentially sensitive because they can contain reasoning summaries and output snippets.
references/throughput-dashboard.js:29Arbitrary Code Execution Through Dynamic Loading of a Workspace Metrics Module
references/drift-guard-auto.js:98Regular Expression Injection Through Unescaped INTENT.md Criteria
Referenced artifact was not completely inspected
| `throughput-dashboard.js` | Weekly productivity metrics | `scripts/` |
Referenced artifact was not completely inspected
| `throughput-dashboard.js` | Weekly productivity metrics | `scripts/` |
Referenced artifact was not completely inspected
| `throughput-dashboard.js` | Weekly productivity metrics | `scripts/` |
Referenced artifact was not completely inspected
| `failure-tracer.js` | Captures traces when quality score < 7 | `lib/` |
Referenced artifact was not completely inspected
| `failure-tracer.js` | Captures traces when quality score < 7 | `lib/` |
Referenced artifact was not completely inspected
| `failure-tracer.js` | Captures traces when quality score < 7 | `lib/` |
Referenced artifact was not completely inspected
| `drift-guard-auto.js` | Weekly INTENT.md compliance scoring | `scripts/` |
Referenced artifact was not completely inspected
| `drift-guard-auto.js` | Weekly INTENT.md compliance scoring | `scripts/` |
Referenced artifact was not completely inspected
| `drift-guard-auto.js` | Weekly INTENT.md compliance scoring | `scripts/` |
Referenced artifact was not completely inspected
| `drift-guard-auto.js` | Weekly INTENT.md compliance scoring | `scripts/` |
The skill description is broad enough to match common requests for observability, debugging, or production monitoring, which increases the chance it is invoked in contexts where the user did not explicitly consent to installing persistent monitoring components. Because the skill copies scripts and libraries into the workspace and encourages recurring cron/heartbeat execution, overbroad activation can silently expand data collection and persistence beyond the user’s immediate intent.
The skill instructs the user to install components that persistently write decision logs, failure traces, dashboards, and drift reports into workspace files, but it does not provide a prominent warning about the privacy, retention, and sensitivity implications of storing reasoning summaries and output snippets. In practice, these logs may capture sensitive operational context, agent outputs, or decision rationale, making accidental data retention and later disclosure more likely.
This is a real integrity issue: the module advertises an append-only audit log, but updateOutcome rewrites the entire file and mutates existing records in place. Audit logs are relied on for tamper-evidence and post-incident reconstruction, so allowing modification of historical entries undermines trust in the log and can enable covering tracks or altering evidence of prior decisions.
This is a real integrity issue in the reporting logic. The scorecard checks for exact keys like 'sycophancy', 'social_cushion', 'unprompted_why', and 'hallucination_hedge', but flagCounts is populated with more specific keys such as 'sycophancy:great choice' after only stripping the occurrence suffix. As a result, the report can falsely claim a dimension is clean even when matching flags were found, undermining audit accuracy and potentially hiding behavioral drift from operators.