Caveat verdict

eir-daily-content-curator

🟢 Trusted

No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Personalized news curation skill that uses a search API (Brave/Tavily) and optional Eir delivery platform; credentials come from environment variables, all external destinations are documented, and the dual-mode design is transparent.

⚠ 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.

security

transparency

maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · frontmatter · API_KEY: "Eir API bearer token (Eir mode only)

Pattern match critical

Writes to SKILL.md — self-modifying skill

references/eir-setup.md · code · SKILL.md for eir-daily-content-curator. Read task files from data/v9/tasks/. For

Pattern match low

Python urllib.request — network access

scripts/connect.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/pipeline/task_builder.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/setup.py · prose · downgraded · shutil.copy(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary.

credential_accesspackage_installnetwork_in

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API