maf-adapter — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited maf-adapter (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill contains the integration specifications and simulation utilities to test and run .md agent skills inside Microsoft's MAF engine (v1.6/v1.7.0).
To test a skill in a simulated MAF execution host locally:
python3 plugins/cli-agents/scripts/test_harness.py \
--skill plugins/exploration-cycle-plugin/skills/exploration-workflow/ \
--input temp/sample_input.txt \
--instruction "Analyze the repository"Before loading a plugin manifest or skill into MAF, validate it against the target runtime criteria:
python3 plugins/cli-agents/scripts/test_harness.py --validate --plugin plugins/exploration-cycle-pluginThis verifies:
plugin.json matches standard keys and is free of banned fields.---) are valid and contain the required name/description.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.