Announcing Beacon: Self-improving memory for coding agents
← All skills
Skill

performing-gcp-security-assessment-with-forseti

skill:mukul975/anthropic-cybersecurity-skills#performing-gcp-security-assessment-with-forseti

Performing comprehensive security assessments of Google Cloud Platform environments using Forseti Security, Security Command Center, and gcloud CLI to audit IAM policies, firewall rules, storage permissions, and compliance against CIS GCP Foundations Benchmark.

Verdict
Suspicious

Risky behavior the analysis could not rule out.

Analyzed Oct 27, 2026, 23:36 UTC at 54a7988

Dispute security verdict

If you believe this verdict is incorrect, submit a dispute and we'll review it.

1
findings
medium
highest severity
1
threat classes
4,532
files scanned
67/67
checks satisfied
0
package advisories

Why this verdict

  • suspicious: finding skill:skills/performing-gcp-security-assessment-with-forseti:skills/performing-gcp-security-assessment-with-forseti/SKILL.md:55:SUPPLY

Security findings 1

Supply chain

mediumContextual riskmedium confidence

The skill's Prerequisites section instructs installing ScoutSuite via the unpinned command `pip install scoutsuite`, so the agent pulls whatever package version is current from PyPI at runtime rather than a reviewed pin.

ScoutSuite installed for multi-cloud comparison (`pip install scoutsuite`)
vector:instruction
Counter-argument considered

The quote is verbatim and the claim accurate: the skill body's Prerequisites section gives the agent a literal unpinned `pip install scoutsuite` command; the official-registry carve-out requires a pin (absent here, and absence of a pin cannot be read as safety), ScoutSuite is not among the declared tools (Forseti Security, SCC, gcloud CLI), and no pin or mitigation appears in any shown unit, so the contextual supply-chain risk survives.