Fulcra Morning Briefing

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: fulcra-morning-briefing Version: 1.0.0 The skill bundle is benign. Its purpose is to collect biometric and calendar data from the Fulcra API and weather data from wttr.in to compose a personalized morning briefing. All network calls are directed to the legitimate Fulcra API (`api.fulcradynamics.com`) and the well-known weather service `wttr.in`. Authentication involves a standard OAuth2 device flow, with the access token stored locally in `~/.config/fulcra/token.json`. The `SKILL.md` instructions for the AI agent are clear, aligned with the stated purpose, and include explicit privacy warnings, showing no evidence of prompt injection or attempts to subvert the agent's behavior. The use of `curl` in `SKILL.md` and `collect_briefing_data.py` is limited to fetching weather data, and there are no signs of data exfiltration, malicious execution, persistence, or obfuscation.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Anyone with access to that token file while it is valid may be able to access sensitive Fulcra data for the account.

Why it was flagged

The skill stores a Fulcra OAuth access token locally so later runs can access the user's Fulcra account data.

Skill content
"access_token": api.fulcra_cached_access_token ... with open(TOKEN_FILE, "w") as f: json.dump(token_data, f, indent=2)
Recommendation

Only authorize this skill if you trust the local agent environment; protect or delete ~/.config/fulcra/token.json when not needed, and revoke/re-authenticate if the token may have been exposed.

What this means

Private health and schedule details can enter the agent's working context and any logs or transcripts associated with the interaction.

Why it was flagged

The collector intentionally places biometric, sleep, calendar, and weather/location data into JSON for the agent to read.

Skill content
Pulls sleep, HR, HRV, calendar from Fulcra API + weather from wttr.in. Outputs structured JSON for an agent
Recommendation

Use this only in agent environments where you are comfortable sharing health and calendar context; avoid forwarding the raw JSON or briefing transcript unnecessarily.

What this means

The weather provider may learn the location or city used for the briefing.

Why it was flagged

The weather feature uses an external weather endpoint and sends the chosen city/location as part of the request.

Skill content
Weather (via wttr.in — no API key needed) ... curl -s "wttr.in/YOUR_CITY?format=j1"
Recommendation

Use a coarse location, such as city rather than exact address, or adapt the skill to use a weather provider you trust.

What this means

Future or unintended versions of the dependency could behave differently from the version the skill author expected.

Why it was flagged

The setup relies on an external Python package without a pinned version in the artifact instructions.

Skill content
pip3 install fulcra-api
Recommendation

Install the package from a trusted source and consider pinning a known-good version in controlled environments.