Security audit

Api Integration

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only frontend API integration skill with coherent, purpose-aligned guidance and no hidden execution or persistence behavior.

Install this skill if you want structured frontend API integration guidance. Review the broad trigger wording if your runtime auto-selects skills aggressively, but no hidden commands, credential access, or persistent behavior were found.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (10)

Credential Access

High

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Content: Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.
md
- Record status codes, error codes, idempotence, retry semantics and time zone/amount/enumeration rules for front-end and back-end collaboration items. 5. Handle authentication refresh - Access token has a short life cycle, and refresh is prioritized in httpOnly cookies or server sessions. - Only a single refresh of the queue is allowed after 401 to avoid multiple requests being refreshed at the same time. - If the refresh fails, you need to clear the local identity status and jump to login. - Do not put bearer token in URL, localStorage or logs.

Skill Enumeration

Medium

Category: Agent Snooping
Confidence: 80% confidence
Finding: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Content: Scanner excerpt · README.md (reported line 10)May include surrounding context.
md
- ID: `fec-api-integration` - Category: `implementation-capability` - Version: `2.9.0` - Source: `skills/fec-api-integration/SKILL.md` ## Description

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description says to use the skill for a wide range of activities including designing, implementing, or reviewing API integration, and then adds a loose list of English and Chinese triggers. This broad phrasing overlaps with common frontend engineering discussions and does not provide explicit trigger constraints or negative examples beyond two exclusions, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description lists many generic topics such as 'designing, implementing, or reviewing frontend-to-backend API integration' and Chinese triggers like 'API integration' and 'front-end and back-end joint debugging', which are broad phrases likely to appear in ordinary engineering discussions. It does include one exclusion, but it does not provide a specific trigger list or negative examples sufficient to clearly distinguish when the skill should and should not activate.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The invocation description is broad and trigger-heavy, covering many common frontend/backend topics and synonyms. In auto-selection environments, this can cause the skill to activate outside its intended scope, exposing users to inappropriate guidance or allowing an attacker to steer the agent toward this skill through prompt wording rather than genuine task fit.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The README explicitly states that Chinese triggers include several phrases, but it does not indicate that language handling is optional or based on user preference. This can be a locale-policy issue because the skill bakes in a specific language without documenting opt-in or a broader multilingual policy.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest description explicitly introduces 'Chinese triggers include ...' but does not state that language selection is optional or user-driven. This creates an implicit language/locale behavior in the skill description without a clear opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The manifest explicitly embeds 'Chinese triggers include ...' but does not state whether multilingual triggering is optional, user-selected, or constrained by runtime locale. This can create a language/locale policy concern because the skill defines language-specific behavior without an explicit opt-in or documented locale policy.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The description lists general-purpose phrases such as 'API integration' and 'front-end and back-end joint debugging' as triggers, which are broad enough to overlap with many ordinary engineering discussions. Although the description adds some exclusions, it does not clearly define a constrained trigger set or negative examples for the listed trigger phrases themselves.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The manifest explicitly states 'Chinese triggers include ...', which introduces a language-specific activation policy in the skill metadata. There is no accompanying indication that language selection is optional or user-configurable, so this may violate the requirement to avoid forcing a specific language or locale without opt-in.
Content: No source excerpt is available for this finding.