jaktestowac/awesome-copilot-for-testers / plugins/testing-llm-guardrails/skills/testing-llm-guardrails
testing-llm-guardrails
FlaggedTests the runtime validation around model output - schema conformance, PII leakage, moderation, refusal behaviour, tool-call safety - and the adversarial suite that tries to defeat it: direct prompt injection, jailbreaks, and indirect injection through retrieved documents, tool results and user content. Use when an LLM feature reaches real users, when a model can call tools or read untrusted content, when an AI feature needs a security-style test suite, or when asked whether a chatbot or agent can be manipulated.
Security report
FlaggedStatic analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.
- Commit
8910672e674853caf0e68dbffc59c39869990203- Content hash
86fd98d4a29f8342654c7e47cde0d019c840fea332d3305b73b0caaf2cdf4655- Scanned
- 2026-11-17
- Scanner version
- skillxone-scan-1.0.0
- Policy version
- 0.1-draft
- Decision
- 1 open critical or high finding.
- Verification expires
- Not applicable
Findings (1 high, 2 low, 1 info)
The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern.
Shapes: direct override of prior instructions; a claim of higher authority ("system message update:", "administrator override"); a claim that the task has changed; instructions embedded in what looks like data; a fake conversation boundary…Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.
The text asks the agent to disclose its system prompt or hidden instructions. Severity lowered from high because the surrounding text warns against it.
- **Prompt instructions are not enforcement.** "Never reveal the system prompt" is a hope. A regex on the output is a check. Authorisation in the tool handler is a control.Suggested fix: Remove the request. A skill has no need to read or reveal the system prompt.
The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern. Severity lowered from high because it appears in a quotation.
- **A corpus, not a handful of tricks.** "Ignore previous instructions" is one case. Categories, versioned and grown from real attempts, is a suite.Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.
The text uses language typical of jailbreak prompts. Severity lowered from medium because the surrounding text warns against it.
- **Indirect injection is the realistic attack.** Nobody needs to type a jailbreak if a retrieved document can carry one. Any feature with retrieval or tool output has this surface.Suggested fix: Remove the jailbreak framing.
Checks run
- prompt-injection
- dangerous-commands
- credentials
- network
- file-access
- integrity
Checks skipped
- dependencies: No dependency manifest in the skill directory.
- gitleaks: gitleaks is not installed on this host.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |