Caveat verdict
SEEM
seem-skill
Episodic memory system using LLM and embedding APIs with user-supplied keys; stores conversation memories locally with all API calls going to user-configured endpoints.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (3)
Possible hardcoded credential
SKILL.md · code · api_key="your-key
Python os.getenv — reads environment variable
config.py · prose · downgraded · os.getenv(
Python shutil file operation — copies/moves/deletes files
core/seem_skill.py · prose · downgraded · shutil.rmtree(
Permissions & capabilities
Requires 2 environment variables. (2 sensitive: LLM_API_KEY, MM_ENCODER_API_KEY). Requires 2 system binaries. (1 elevated: pip).
data_encodingpackage_install Is this flag fair?
Thanks — recorded.