SkillSpector · watchers

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

scripts/watch_github.py

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

scripts/watch_github.py

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

scripts/watch_github.py

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/watch_github.py

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/watch_github.py

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

scripts/watch_http_json.py

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

scripts/_watermark.py

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

SKILL.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

scripts/watch_github.py

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

scripts/_watermark.py

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

scripts/watch_github.py