PUAClaw

PUAClaw is a documentation-first framework for classifying and organizing prompt-based psychological persuasion / unconventional rhetoric techniques used with LLMs. The repository primarily provides taxonomies, technique categories, templates/“prompt” wording examples, and related documentation (e.g., glossary, FAQ, technique index), rather than a software service or API.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-ml prompt-engineering documentation taxonomy red-teaming evaluation misuse-detection security
⚙ Agent Friendliness
22
/ 100
Can an agent use this?
🔒 Security
16
/ 100
Is it safe for agents?
⚡ Reliability
12
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
40
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
0
Scope Granularity
0
Dep. Hygiene
30
Secret Handling
60

Security posture cannot be assessed from the provided excerpts because there is no code/API details, dependency manifest, or deployment description. However, the content explicitly organizes and describes psychological coercion techniques for LLM prompts; this increases misuse risk if used to generate persuasive/manipulative prompts in real settings. No evidence is provided for secure development practices, secrets handling, or transport security.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
20
Error Recovery
0
AF Security Reliability

Best When

You need a structured reference taxonomy for analyzing or categorizing prompt-based persuasion techniques in an offline/documentation context.

Avoid When

You need a reliable, security-hardened software library or an API for runtime use; or you intend to use the provided technique templates to apply coercion in real-world settings.

Use Cases

  • Researching and documenting prompt-injection/behavior-manipulation patterns in LLM prompts (taxonomy/recordkeeping)
  • Building internal evaluations or red-teaming taxonomies for prompt-based coercion attempts
  • Studying psychological influence patterns as they appear in prompt engineering and LLM interactions (academic/educational)
  • Creating moderation/classification datasets or rubrics to detect persuasive/unconventional prompt patterns

Not For

  • Operational deployment to manipulate users or influence decisions
  • Anything intended to coerce real people or produce targeted psychological harm
  • A toolchain expecting a programmatic API/SDK to call or integrate into production systems

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication is applicable: this appears to be a documentation/repo framework rather than an API/service.

Pricing

Free tier: No
Requires CC: No

No pricing details provided; repository content suggests it is freely accessible as documentation (MIT license).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • This is not an executable software service; agents expecting endpoints/tools will find none.
  • The repository content includes examples/taxonomies related to coercive persuasion; using those as-is could be disallowed depending on the agent’s policy and the surrounding system’s safety rules.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for PUAClaw.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6461
Packages Evaluated
19942
Need Evaluation
586
Need Re-evaluation
Community Powered