Apache Tika is a toolkit that reads many kinds of files and extracts their text and descriptive metadata, including from formats such as PDF, PowerPoint, and Excel. Applications and agent pipelines use it to turn documents into content they can process, search, or pass to language models. The catalogue skills provide reusable ways for coding agents to run Tika for file-to-Markdown extraction.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/apache/tikanpx agentmods add skills/apache/tika/oss-fuzzWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/apache/tika/oss-fuzz)<a href="https://agentmods.dev/skills/apache/tika/oss-fuzz"><img src="https://agentmods.dev/badge/skills/apache/tika/oss-fuzz/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/apache/tika/oss-fuzz"><img src="https://agentmods.dev/badge/skills/apache/tika/oss-fuzz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 143 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 180 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 254 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 289 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 327 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.05047 |
| Opus 5.5 | $0.00036 | $0.02019 |
| Sonnet 5.5 | $0.00018 | $0.01009 |
| Haiku 4.5 | $0.00009 | $0.00505 |
Grade A, and why
oss-fuzz scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local override: $TIKA_SKILLS_LOCAL/oss-fuzz/LOCAL.md (default ~/.tika-skills),
read after this file, wins on conflict.
Tika OSS-Fuzz — local fuzzing
Tika is already in OSS-Fuzz as the apache-tika project (not tika).
It is Jazzer-based (coverage-guided, in-process JVM fuzzing), not the old
tika-fuzzing seed-mutation module (removed in TIKA-4506). The fuzz targets
and seed logic live in the oss-fuzz repo under
projects/apache-tika/, not in this repo:
project-parent/fuzz-targets/src/main/java/com/example/*Fuzzer.java— one Jazzer target per parser family. Each callsParserFuzzer.parseOne(...)(parse-from-bytes and parse-from-file) and swallowsTikaException | SAXException | IOException; anything else —Error(OOM, StackOverflow), a hang, or an unexpectedRuntimeException— is a finding.build.sh— buildstika-app, then thefuzz-targetsmodule.build_seeds.sh— packs Tika's own unit-test files into<Target>_seed_corpus.zipby file extension.
Targets (as of this writing): AudioVideoParsersFuzzer,
AutoDetectParserFuzzer, CompressorParserFuzzer, HtmlParserFuzzer,
ImageParsersFuzzer, JackcessParserFuzzer, OOXMLParserFuzzer,
OfficeParserFuzzer, OneNoteParserFuzzer, PDFParserFuzzer,
PackageParserFuzzer, RFC822ParserFuzzer, RTFParserFuzzer,
TextAndCSVParserFuzzer, XMLReaderUtilsFuzzer. ParserFuzzer is the shared
helper, not a target (build.sh skips it). This list drifts — get the current
one after a build with ls build/out/apache-tika/*Fuzzer, or from source with
find $OSSFUZZ/projects/apache-tika/project-parent/fuzz-targets -name '*Fuzzer.java'.
Primary contact on the project is [email protected], so OSS-Fuzz crash
mail / ClusterFuzz notifications land in that inbox — check there for what
continuous fuzzing has already found before treating a bug as newly discovered.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 362 lines · 90 tokens per session scan A 188ff5536da1
oss-fuzz is a skill published in the GitHub repository apache/tika (4,098 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 5,047 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
java-affected-tests
Use before opening or updating an OpenMetadata PR that changes Java, a JSON schema, an index mapping, a SQL migration, seed data or a pom — PR CI no longer runs the Java integration tests (they run only in the merge queue) and the JavaUIIT/search-it suites run only nightly, so this selects the unit tests and…
playwright-validation
Use when validating UI changes in a branch require Playwright E2E testing. Reviews branch changes, validates UI with Playwright MCP, and adds missing test cases.
playwright-test
Generate robust, zero-flakiness Playwright E2E tests following OpenMetadata patterns. Creates comprehensive test files with proper waits, API validation, multi-role permissions, and complete entity lifecycle management.
tdd
Use when implementing new features or fixing bugs to enforce test-driven development. Guides the RED-GREEN-REFACTOR cycle for Java (JUnit), Python (pytest), and TypeScript (Jest/Playwright) in OpenMetadata.
test-locally
Build and deploy a full local OpenMetadata stack with Docker to test your connector in the UI. Handles code generation, build optimization, health checks, and guided testing.
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.