aws-iam-enum

Enumerate AWS IAM policies, detect privilege escalation paths per Rhino Security Labs canonical 21 primitives.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/cloud/aws-iam-enum/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with concrete AWS CLI commands and a useful privesc reference, but commands rely on unexplained placeholders and the workflow lacks explicit validation checkpoints.

Suggestions

Replace generic placeholders (ME, ARN, VID, <vuln>) with concrete worked examples or a short note on how to populate them (e.g. capture caller identity into a variable first).

Add a validation checkpoint after fetching policies (e.g. confirm `/tmp/policy.json` is valid JSON before calling `iam_policy_audit`) to close the workflow-clarity gap.

Define or link the `kg_add_node`/`kg_add_edge` helpers so the graph-promotion block is executable rather than assumed.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-block-driven with no re-explanation of concepts Claude already knows; the 21-primitive list is dense reference data where every token earns its place, matching the level-3 anchor.	3 / 3
Actionability	Concrete AWS CLI commands are present, but many require substitution (e.g. `--user-name ME`, `ARN`, `VID`, `<vuln>`) and `kg_add_node`/`kg_add_edge` are undefined placeholders, so it is not fully copy-paste ready as required for level 3.	2 / 3
Workflow Clarity	Sections 1–5 give a clear sequenced process (identity → policies → privesc → graph → chains), but there are no validation checkpoints (e.g. verifying caller-identity succeeds or confirming policy JSON parsed) before proceeding, which is the level-2 anchor.	2 / 3
Progressive Disclosure	No bundle files exist and none are needed; the skill is self-contained and well-organized into clearly labeled numbered sections, which the simple-skill scoring note allows to score 3.	3 / 3
	Total	10 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive but lacks an explicit "Use when..." trigger clause and leans on specialized jargon ("Rhino Security Labs canonical 21 primitives") that limits natural trigger-term quality.

Suggestions

Add a "Use when..." clause naming natural user triggers, e.g. "Use when auditing AWS IAM permissions or hunting for privilege-escalation paths in an AWS account."

Soften jargon in the description itself (keep "Rhino Security Labs 21 primitives" for context but lead with plain terms like "privilege escalation" / "privesc").

Include common natural variations ("AWS IAM", "IAM policies", "privesc", "privilege escalation") so the description matches how users phrase the need.

Dimension	Reasoning	Score
Specificity	The phrase "Enumerate AWS IAM policies, detect privilege escalation paths" names multiple specific concrete actions, matching the level-3 anchor rather than the level-2 anchor which only names a domain and some actions.	3 / 3
Completeness	It clearly answers "what" (enumerate policies, detect privesc) but has no "Use when..." or equivalent explicit trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	"AWS IAM", "policies", and "privilege escalation" are relevant keywords a user might say, but "Rhino Security Labs canonical 21 primitives" is technical jargon and common variations (e.g., "privesc", "escalation paths") are thin, so it does not reach full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	"AWS IAM" enumeration and privilege-escalation detection is a clear niche with distinct triggers unlikely to collide with other skills, matching the level-3 anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/cloud/aws-iam-enum/SKILL.md
Commit: e34afba

Reviewed: about 16 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.