Grant Application Writer
v1.0.0Write compelling grant applications and funding proposals for UK charities, social enterprises, researchers, and small businesses. Generates need statements,...
⭐ 0· 57·0 current·0 all-time
byExternalOS@jamespatrickthom2003-star
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (grant application writer) match the SKILL.md, README, and listing: the skill focuses on producing need statements, budgets, theory of change, M&E, risk registers and funder-specific language for UK funders. It does not request unrelated credentials, binaries, or config paths — nothing appears disproportionate to the stated function.
Instruction Scope
The runtime instructions stay on-topic (ask clarifying questions, produce full application sections, adapt language to named funders). Two non-security concerns to be aware of: (1) the skill instructs the model to 'cite specific sources' (ONS, JSNA, academic research) — this can lead to hallucinated or unverified citations so outputs should be checked; (2) users may paste project documents containing personal data (beneficiaries, sensitive info) — the skill does not declare guidance for handling pasted PII beyond generic GDPR notes in README, so users should avoid sending sensitive personal identifiers.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low risk from an installation perspective — nothing is downloaded or written to disk by an installer.
Credentials
No environment variables, credentials, or config paths are required. The skill's functionality does not request access to unrelated services or secrets.
Persistence & Privilege
always:false and user-invocable:true; autonomous invocation is allowed (disable-model-invocation:false) which is the platform default and expected for skills. The skill does not request persistent system-wide privileges or modify other skills.
Assessment
This skill appears coherent and low-risk from a platform/infrastructure standpoint, but consider these practical cautions before use: (1) Verify facts, figures and citations — the model may invent sources or misstate statistics; always cross-check any ONS, academic or local authority references. (2) Do not paste or ask the skill to handle sensitive personal data (names, contact details, health information, or identifiers for beneficiaries) unless you have explicit consent and a secure process — treat pasted beneficiary data as a disclosure risk. (3) Check funder guidance and compliance details yourself (deadlines, application forms, word limits, formatting, eligibility, DBS/safeguarding requirements, GDPR obligations) — the skill helps draft content but cannot submit applications or guarantee eligibility. (4) Have a finance or grants officer review budgets, unit rates, match-funding and procurement assumptions before submission. (5) Test outputs on small, non-sensitive prompts first to confirm tone/format and to detect any hallucinated citations or incorrect policy references. No special system permissions or credentials are requested by this skill.Like a lobster shell, security has layers — review code before you run it.
applicationvk972qcf1gyjjxfmvmkqf4hv1hd84f9mccharityvk972qcf1gyjjxfmvmkqf4hv1hd84f9mcfundingvk972qcf1gyjjxfmvmkqf4hv1hd84f9mcgrantvk972qcf1gyjjxfmvmkqf4hv1hd84f9mclatestvk972qcf1gyjjxfmvmkqf4hv1hd84f9mcresearchvk972qcf1gyjjxfmvmkqf4hv1hd84f9mcukvk972qcf1gyjjxfmvmkqf4hv1hd84f9mc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
