Time Anchor
PassAudited by VirusTotal on May 6, 2026.
Overview
Type: OpenClaw Skill Name: time-anchor Version: 1.1.0 The 'time-anchor' skill is a utility for performing deterministic date calculations and tracking specific milestones. The Python script (time-anchor.py) uses standard libraries to calculate time deltas and handle weekday ambiguity without any network access, file system manipulation, or credential access. The instructions in SKILL.md are focused on guiding the agent's logic for temporal reasoning and do not contain any prompt-injection attacks or malicious directives.
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.
The agent may run a bundled local script when answering date questions, but the reviewed script only performs date calculations and prints results.
The skill's normal operation involves local Python execution; this is disclosed and central to the date-math purpose.
Use `exec` to run the bundled script instead of doing date math yourself.
Install only if you are comfortable with the agent executing this bundled script, and review any future edits to the file before relying on it.
For unknown events, the agent may search the web instead of immediately asking you for the date.
The workflow allows an external lookup for unknown named events before asking the user; this is purpose-aligned but could disclose the event name to a search provider.
Still unsure? Web search. STILL unsure? Ask which occurrence they mean.
If an event name is private or internal, tell the agent not to web-search it and provide the date directly.
Any custom event names or dates added to the script can persist locally and influence future date calculations.
The documentation supports persistent local customization of named dates, so added goals may be reused in later answers.
Edit `~/.openclaw/workspace/skills/time-anchor/scripts/time-anchor.py`, add to the `TARGETS` dict
Avoid storing sensitive event names in the TARGETS dictionary, or keep labels generic if the skill directory may be shared or backed up.