Results for “trustscore”

Checks on-chain agent trustworthiness, discovers agents for tasks, profiles agents, looks up wallet/identity records, contacts or dispatches agents, and reads or writes hosted metadata via the 8K4 Protocol (ERC-8004).

Compute the F1Score metric using torchmetrics when predictions and ground-truth labels are available.

Assigns behavioral trust grades (A–F) to MCP servers by running probes for prompt injection, permission overreach, data leaks, and adversarial-input handling, and publishes reproducible onchain attestations.

Computes the R2Score metric using torchmetrics, handling single and multi-output predictions with options for adjusted and variance-weighted scores.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Benchmarks a text-to-text transformer across GLUE, SuperGLUE, CNN/Daily Mail, SQuAD, and WMT, reporting GLUE average, BLEU, ROUGE-2-F, and Exact Match scores.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Validates the Emotional Attitude Score (EAS) metric by measuring its consistency with human judgment on word-level sentiment polarity, using the AmbGIMT dataset and pairwise score comparisons.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.