Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation handoff skill that may create a requirements Markdown file, with no evidence of hidden execution, credential access, exfiltration, or persistence.
Installers should treat this as a documentation helper. Before use, confirm whether the agent should create a repository file or answer in chat only, and review the generated requirements document before committing it because it may summarize product rules, permissions, and UI behavior.
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.
- ID: `fec-backend-requirements-handoff`
- Category: `maintenance-docs`
- Version: `2.9.0`
- Source: `skills/fec-backend-requirements-handoff/SKILL.md`
## Description
The README says to use the skill whenever frontend work needs to communicate a wide range of needs to backend teams, and lists broad phrases like 'back-end requirements' and 'API requirements clarification.' Without explicit constraints or negative examples, these triggers could overlap with common product or engineering discussions and cause unintended invocation.
The manifest description says to use the skill whenever frontend work needs to communicate various needs to backend teams, and includes generic trigger phrases like "back-end requirements" and "API requirements clarification." These phrases are broad enough to overlap with ordinary discussion requests, and the file does not provide explicit exclusion conditions or negative examples to narrow when the skill should or should not activate.
The manifest description defines very broad activation language such as 'frontend work needs to communicate' and 'API requirements clarification,' which can cause the skill to be invoked outside narrowly intended scenarios. In an agent ecosystem, ambiguous triggers increase the chance of inappropriate routing, causing the skill to shape conversations or outputs where a more suitable skill or no skill should have been used.
The description explicitly includes Chinese trigger phrases, while the rest of the skill is written in English and does not explain whether language handling is optional or user-selected. This can create a locale-policy issue because it introduces language-specific activation behavior without documenting user choice or a justified region-specific scope.
The skill states that it will write output to a default path unless the user only needs chat replies, but it does not require an explicit confirmation step before modifying the repository. In agent environments, implicit file-writing can cause unintended workspace changes, accidental disclosure in committed docs, or surprise side effects when a user expected analysis-only behavior.
The description explicitly states that Chinese triggers include certain phrases, but does not indicate that language selection is optional or user-driven. This can violate language/locale policy expectations because it prescribes a specific language behavior without documenting user choice or a justified regional constraint.
No suspicious patterns detected.