google-photos
What this skill does
A CLI and agent skill for interacting with Google Photos Library and Picker APIs, enabling operations like creating albums, importing data, and managing media.
github/mvanhorn - Data Exfiltration - 1.9k stars
Threat analysis
Skill info
pkg:github/mvanhorn/printing-press-library@5a78746?skill=google-photosAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
internal/cli/import.go
The `import` command reads data from a JSONL file and sends it to an API endpoint via POST requests. If the API endpoint is not properly secured or if the data being sent is sensitive, this could leadInsecure Defaults
Insecure Defaults via local-llm-review
internal/cache/cache.go
The cache implementation stores JSON responses as flat files in `~/.cache/<cli>/` with a TTL. If the cache directory is not properly secured, this could lead to sensitive data being exposed.Badge
Add the Anomity scan badge for google-photos to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of google-photos? Report an issue or request a rescan.
