# Power Automate Run Forensics

> >

- **Type:** Skill
- **Install:** `agentstack add skill-wals-pro-claude-power-automate-power-automate-run-forensics`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Wals-pro](https://agentstack.voostack.com/s/wals-pro)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Wals-pro](https://github.com/Wals-pro)
- **Source:** https://github.com/Wals-pro/claude-power-automate/tree/main/skills/power-automate-run-forensics

## Install

```sh
agentstack add skill-wals-pro-claude-power-automate-power-automate-run-forensics
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Power Automate Run Forensics

Start read-only. Confirm what the flow actually did before changing JSON,
connections, or production records.

## Procedure

1. Define boundary: profile, environment ID, flow ID/name, run ID(s), object IDs,
   and absolute time window.
2. Run `power-automate status --profile ` and
   `power-automate runs --profile ` when API access is available.
3. If the flow or environment is unknown, run `power-automate environments`,
   `power-automate flows`, or `power-automate runs --all-environments --top `
   to discover what the signed-in Azure user can see.
4. For a failed or suspicious run, inspect `power-automate run-detail`.
5. Compare trigger data, action inputs, action outputs, branch status, skipped
   actions, and connector error codes.
6. Read `references/errors-limits.md` for Microsoft error/limit guidance.
7. Produce findings before proposing edits.

## Output

Report:

- Boundary checked.
- Evidence reviewed.
- Findings with run IDs and timestamps.
- Impact.
- Root cause or strongest hypothesis.
- Fix target and validation plan.

If evidence is missing, name the missing source and why it matters.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Wals-pro](https://github.com/Wals-pro)
- **Source:** [Wals-pro/claude-power-automate](https://github.com/Wals-pro/claude-power-automate)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-wals-pro-claude-power-automate-power-automate-run-forensics
- Seller: https://agentstack.voostack.com/s/wals-pro
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.